7.1.1 ACTA

• Name:
  A Tool for Argumentative Clinical Trial Analysis
• Keywords:
  Artificial intelligence, Natural language processing, Argument mining
• Functional Description:
  Argumentative analysis of textual documents of various nature (e.g., persuasive essays, online discussion blogs, scientific articles) allows to detect the main argumentative components (i.e., premises and claims) present in the text and to predict whether these components are connected to each other by argumentative relations (e.g., support and attack), leading to the identification of (possibly complex) argumentative structures. Given the importance of argument-based decision making in medicine, ACTA is a tool for automating the argumentative analysis of clinical trials. The tool is designed to support doctors and clinicians in identifying the document(s) of interest about a certain disease, and in analyzing the main argumentative content and PICO elements. In 2024, ACTA has been integrated in a suite called ANTIDOTE, which collects the software results from the ANTIDOTE project (all partners).
• URL:
  http://­antidote.­i3s.­unice.­fr/­acta/
• Contact:
  Serena Villata

7.1.2 ARViz

• Name:
  Association Rules Visualization
• Keyword:
  Information visualization
• Scientific Description:
  ARViz supports the exploration of data from named entities knowledge graphs based on the joint use of association rule mining and visualization techniques. The former is a widely used data mining method to discover interesting correlations, frequent patterns, associations, or casual structures among transactions in a variety of contexts. An association rule is an implication of the form X -> Y, where X is an antecedent itemset and Y is a consequent itemset, indicating that transactions containing items in set X tend to contain items in set Y. Although the approach helps reduce and focus the exploration of large datasets, analysts are still confronted with the inspection of hundreds of rules in order to grasp valuable knowledge. Moreover, when extracting association rules from named entities (NE) knowledge graphs, the items are NEs that form antecedent -> consequent links, which the user should be able to cross to recover information. In this context, information visualization can help analysts visually identify interesting rules that are worthy of further investigation, while providing suitable visual representation to communicate the relationships between itemsets and association rules.
• Functional Description:
  ARViz supports the exploration of thematic attributes describing association rules (e.g. confidence, interestingness, and symmetry) through a set of interactive, synchronized, and complementary visualisation techniques (i.e. a chord diagram, an association graph, and a scatter plot). Furthermore, the interface allows the user to recover the scientific publications related to rules of interest.
• Release Contributions:
  Visualization of association rules within the scientific literature of COVID-19.
• Publication:
  hal-03292140
• Contact:
  Marco Alba Winckler
• Participants:
  Aline Menin, Lucie Cadorel, Andrea Tettamanzi, Alain Giboin, Fabien Gandon, Marco Alba Winckler

7.1.3 Attune

• Name:
  Attune - A Web-Based Digital Audio Workstation to Empower Cochlear Implant Users
• Keywords:
  Web Application, Audio signal processing, Plug-in
• Functional Description:
  Attune is an online software based on the Wam-Studio open-source digital audio workstation, adapted to help cochlear implant users perceive music more clearly. During multi-track listening, simple settings such as "clarity", "power", "attenuation" can be used. In reality, these settings control many parameters of sound processing plugins, which operate behind the scenes. The mapping between these plugins and the settings offered to users is carried out by researchers, using a dedicated graphical interface and a powerful macro management system.
• Contact:
  Michel Buffa
• Partner:
  CCRMA Lab, Stanford

7.1.4 CORESE-Core

• Name:
  COnceptual REsource Search Engine - Core
• Keywords:
  Semantic Web, RDF, RDFS, SPARQL, OWL, SHACL, Automated Reasoning, Validation, Interoperability, Linked Data, Knowledge Graphs, Knowledge Bases, Knowledge representation, Querying, Ontologies
• Scientific Description:
  CORESE-Core is a library used in research to apply and evaluate Semantic Web standards and the algorithms they require. It is also the basis for proposing and prototyping extensions to these standards and their processing.
• Functional Description:

  CORESE-Core is a library that implements and extends the Semantic Web standards established by the W3C, such as RDF, RDFS, SPARQL1.1 Query & Update, OWL RL, SHACL, and others.

  This library offers a wide range of features for creating, manipulating, parsing, serializing, querying, reasoning and validating RDF data.

  In addition, it offers advanced extensions such as STTL, SPARQL Rule and LDScript, which extend the functionality and processing capabilities of the data.

  NB: CORESE-Core is a library derived from the earlier CORESE software.

• Release Contributions:
  https://github.com/Wimmics/corese/blob/master/CHANGELOG.md
• URL:
  http://­project.­inria.­fr/­corese
• Contact:
  Remi Ceres
• Participants:
  Remi Ceres, Fabien Gandon

7.1.5 CORESE-GUI

• Name:
  COnceptual REsource Search Engine - Graphical User Interface
• Keywords:
  GUI (Graphical User Interface), User Interfaces, Knowledge Bases, Knowledge Graphs, Knowledge graph, Knowledge representation, Ontologies, Linked Data, Validation, Automated Reasoning, SHACL, OWL, SPARQL, RDFS, RDF, Querying, Applications
• Scientific Description:
  CORESE-GUI is a graphical user interface developed to interact with the CORESE-Core library. It provides users, especially those less experienced in programming, with an intuitive and visual access to the functionalities of CORESE-Core. This interface includes tools for visualizing semantic data, editing SPARQL queries, and monitoring data processing results. CORESE-GUI also serves as a platform for experimenting with new extensions and processing methods in the field of semantic web, thereby making these technologies more accessible to researchers and practitioners.
• Functional Description:

  This desktop application allows the user to call up CORESE-Core features for creating, manipulating, parsing, serializing, querying, reasoning and validating RDF data.

  The application enables direct use of Semantic Web languages standardized by the W3C, such as RDF and its syntaxes, RDFS, SPARQL1.1 Query & Update, OWL RL, SHACL, and others.

• URL:
  http://­project.­inria.­fr/­corese
• Contact:
  Remi Ceres
• Participants:
  Remi Ceres, Fabien Gandon

7.1.6 CORESE-Server

• Name:
  COnceptual REsource Search Engine - Server
• Keywords:
  Server, Linked Data, Semantic Web, Ontologies, Knowledge Graphs, Knowledge Bases, RDF, RDFS, SPARQL, SHACL, Querying, Validation, Automated Reasoning
• Scientific Description:
  This server version allows remote applications to access CORESE-Core functionalities for creating, manipulating, analyzing, serializing, querying, reasoning, and validating RDF data. The server facilitates remote use of W3C-standardized Semantic Web languages, such as RDF and its syntaxes, RDFS, SPARQL1.1 Query & Update, OWL RL, SHACL, and more.
• Functional Description:

  This server version enables a remote application to call CORESE-Core's functions for creating, manipulating, analyzing, serializing, querying, reasoning and validating RDF data.

  The server enables remote use of Semantic Web languages standardized by the W3C, such as RDF and its syntaxes, RDFS, SPARQL1.1 Query & Update, OWL RL, SHACL, and others.

• URL:
  https://­project.­inria.­fr/­corese/
• Contact:
  Remi Ceres
• Participants:
  Remi Ceres, Fabien Gandon

7.1.7 CORESE-Command

• Name:
  COnceptual REsource Search Engine - Command Line
• Keywords:
  Command, RDF, RDFS, SPARQL, SHACL, Knowledge acquisition
• Scientific Description:
  This command-line version of CORESE enables users to incorporate CORESE-Core functionalities into scripts, workflows, and consoles for creating, manipulating, analyzing, serializing, querying, reasoning, and validating RDF data. It allows direct use of W3C-standardized Semantic Web languages, such as RDF and its syntaxes, RDFS, SPARQL1.1 Query & Update, OWL RL, SHACL, and more.
• Functional Description:

  This command-line version enables users to call CORESE-Core's functionality in scripts, workflows and console mode for the creation, manipulation, analysis, serialization, querying, reasoning and validation of RDF data.

  The command enables direct use of W3C-standardized Semantic Web languages, such as RDF and its syntaxes, RDFS, SPARQL1.1 Query & Update, OWL RL, SHACL, and others.

• URL:
  https://­project.­inria.­fr/­corese/
• Contact:
  Remi Ceres
• Participants:
  Remi Ceres, Fabien Gandon

7.1.8 CROBORA

• Name:
  Crossing borders Archives. The circulation of images of Europe.
• Keywords:
  Audiovisual, Data visualization
• Functional Description:
  This platform gives access to 36 000 stock shots reused in the evening news of six national channels in France and Italy (France 2, Arte, TF1, Rai Uno, Rai Due and Canale 5) and the YouTube accounts of the European institutions between 2001 and 2021. The platform gives access four types of data: screenshots (one for each stock shot), metadata (for each stock shot), videos (news), and original metadata for each video. The platform integrates three visualization tools (Treemaps, Muvin, and ArViz) presenting patterns and relationships between records. The tool is available at https://crobora.huma-num.fr/crobora?tab=0
• Contact:
  Marco Alba Winckler

7.1.9 Datalens

• Keywords:
  Data visualization, Artificial intelligence
• Functional Description:
  Datalens leverages custom network topologies, multi-faceted filters, and advanced visualization techniques to help users discover relevant datasets published online for their specific tasks. It harnesses the visualization capabilities of MGExplorer to enable a multi-perspective exploration of data. Currently, the tool supports navigation through datasets and models available on HuggingFace.
• URL:
  https://­dataviz.­i3s.­unice.­fr/­datalens/
• Contact:
  Aline Menin

7.1.10 DBpedia

• Name:
  DBpedia
• Keywords:
  RDF, SPARQL
• Functional Description:
  DBpedia is an international crowd-sourced community effort to extract structured information from Wikipedia and make this information available on the semantic Web as linked open data. The DBpedia triple stores then allow anyone to solve sophisticated queries against Wikipedia extracted data, and to link the different data sets on these data. The French chapter of DBpedia was created and deployed by Wimmics and is now an online running platform providing data to several projects such as: QAKIS, Izipedia, zone47, Sépage, HdA Lab., JocondeLab, etc.
• Release Contributions:
  The new release is based on updated Wikipedia dumps and the inclusion of the DBpedia history extraction of the pages.
• URL:
  http://­wiki.­dbpedia.­org/
• Contact:
  Fabien Gandon
• Participants:
  Fabien Gandon, Elmahdi Korfed

7.1.11 Fuzzy labelling argumentation module

• Name:
  Fuzzy labelling algorithm for abstract argumentation
• Keywords:
  Artificial intelligence, Multi-agent, Knowledge representation, Algorithm
• Functional Description:
  The goal of the algorithm is to compute the fuzzy acceptability degree of a set of arguments in an abstract argumentation framework. The acceptability degree is computed from the trustworthiness associated with the sources of the arguments.
• Contact:
  Serena Villata
• Participant:
  Serena Villata

7.1.12 GUsT-3D

• Name:
  Guided User Tasks Unity plugin for 3D virtual reality environments
• Keywords:
  3D, Virtual reality, Interactive Scenarios, Ontologies, User study
• Functional Description:

  We present the GUsT-3D framework for designing Guided User Tasks in embodied VR experiences, i.e., tasks that require the user to carry out a series of interactions guided by the constraints of the 3D scene. GUsT-3D is implemented as a set of tools that support a 4-step workflow to : (1) annotate entities in the scene with names, navigation, and interaction possibilities, (2) define user tasks with interactive and timing constraints, (3) manage scene changes, task progress, and user behavior logging in real-time, and (4) conduct post-scenario analysis through spatio-temporal queries on user logs, and visualizing scene entity relations through a scene graph.

  The software also includes a set of tools for processing gaze tracking data, including: cleaning and synchronization of the data, calculation of fixations with I-VT, I-DT, IDTVR, IS5T, Remodnav, and IDVT algorithms, and visualization of the data (points of regard and fixations) in both real time and collectively.

• URL:
  https://­project.­inria.­fr/­creattive3d/­gust-3d/
• Publications:
  hal-04102737, hal-04446066, hal-03635452
• Contact:
  Hui-Yin Wu
• Participants:
  Hui-Yin Wu, Marco Alba Winckler, Lucile Sassatelli, Florent Robert
• Partner:
  I3S

7.1.13 IndeGx

• Keywords:
  Semantic Web, Indexation, Metadata
• Functional Description:
  IndeGx is a framework for the creation of an index of a set of SPARQL endpoints. The framework relies only on available semantic web technologies and the index appears as an RDF database. The index is primarily composed of the self-description available in the endpoint. This original description is verified and expanded by the framework, using SPARQL queries.
• Release Contributions:

  The previous version was a Java application coded with Apache Jena, this version uses an engine coded in Typescript with rdflib, graphy, sparqljs, coupled with a Corese Server, in a docker application. - Treatment of endpoints in parallel -The automatic pagination of simple queries to avoid overwhelming SPARQL endpoints. - The usage of Corese as an interface with SPARQL endpoints to reduce missing data due to errors coming from incorrect standard compliance in distant SPARQL endpoints. - Rules are now expected to make heavy use of federated querying, with the SERVICE clause. - Possibility to define the application of several rules as a prerequisite to the application of another. - End of the difference between CONSTRUCT and UPDATE rules to differentiate between the application of local and distant queries. Only test queries are supposed to be SELECT, ASK, or CONSTRUCT. All action queries are expected to be UPDATE queries. - Possibility to define a set of rules as a pre-treatment or a post-treatment on the extracted data. In this case, the endpoint URL becomes the URL of the local corese server (not accessible from the outside of the docker) - Handling many different errors in the RDF format of data found in remote endpoints - Possibility of disabling the query logging of the framework - Possibility of using the query logging of the framework to avoid repeating rule application in case of an execution interruption - Integration of LDscript in rules possible.

  We also offer two automatically refreshed catalogs, - The catalog of endpoints taken from numerous sources, updated daily - The catalog of endpoints and their statuses, refreshed hourly

• URL:
  https://­github.­com/­Wimmics/­IndeGx
• Publication:
  hal-03946680v1
• Contact:
  Pierre Maillot
• Participants:
  Fabien Gandon, Catherine Faron, Olivier Corby, Franck Michel

7.1.14 ISSA-pipeline

• Name:
  Processing pipeline of the ISSA project
• Keywords:
  Indexing, Semantic Web, Knowledge Graphs, NLP
• Functional Description:
  See the description at https://github.com/issa-project/issa-pipeline/tree/main/pipeline
• Release Contributions:
  Add bibliometric indicators and new visualizations. Details: https://github.com/issa-project/issa-pipeline/compare/2.0...2.1
• URL:
  https://­github.­com/­issa-project/­issa-pipeline
• Contact:
  Franck Michel
• Participants:
  Anna Bobasheva, Franck Michel

7.1.15 ISSA Visualization Web Application

• Keywords:
  Open Access, Data visualization, Knowledge graph, NLP
• Functional Description:
  The ISSA project focuses on the semantic indexing of scientific publications in an open archive. The ISSA Visualization Web Application is a React and node.js based web application meant to search articles from the ISSA knowledge base using the rich semantics of the reference vocabularies, and provide a visualization of their metadata. This application consists of a frontend and a backend hosted on separate repositories: https://github.com/issa-project/web-visualization/ https://github.com/issa-project/web-backend
• URL:
  https://­github.­com/­issa-project/­web-visualization/
• Contact:
  Franck Michel
• Participant:
  Franck Michel
• Partners:
  CIRAD, IMT Mines Alès

7.1.16 KartoGraphI

• Functional Description:
  Website displaying a screenshot of the state of the Linked Data web according to the description retrieved by the IndeGx software
• URL:
  http://­prod-dekalog.­inria.­fr/
• Publication:
  hal-03652865
• Contact:
  Pierre Maillot

7.1.17 Licentia

• Keywords:
  Right, License
• Scientific Description:
  In order to ensure the high quality of the data published on the Web of Data, part of the self-description of the data should consist in the licensing terms which specify the admitted use and re-use of the data by third parties. This issue is relevant both for data publication as underlined in the “Linked Data Cookbook” where it is required to specify an appropriate license for the data, and for the open data publication as expressing the constraints on the reuse of the data would encourage the publication of more open data. The main problem is that data producers and publishers often do not have extensive knowledge about the existing licenses, and the legal terminology used to express the terms of data use and reuse. To address this open issue, we present Licentia, a suite of services to support data producers and publishers in data licensing by means of a user-friendly interface that masks to the user the complexity of the legal reasoning process. In particular, Licentia offers two services: i) the user selects among a pre-defined list those terms of use and reuse (i.e., permissions, prohibitions, and obligations) she would assign to the data and the system returns the set of licenses meeting (some of) the selected requirements together with the machine readable licenses’ specifications, and ii) the user selects a license and he/she can verify whether a certain action is allowed on the data released under such license. Licentia relies on the dataset of machine-readable licenses (RDF, Turtle syntax, ODRL vocabulary and Creative Commons vocabulary) available at http://datahub.io/dataset/rdflicense. We rely on the deontic logic to address the problem of verifying the compatibility of the licensing terms in order to find the license compatible with the constraints selected by the user. The need for licensing compatibility checking is high, as shown by other similar services (e.g., Licensius or Creative Commons Choose service). However, the advantage of Licentia with respect to these services is twofold: first, in these services compatibility is pre-calculated among a pre-defined and small set of licenses, while in Licentia compatibility is computed at runtime and we consider more than 50 heterogeneous licenses, second, Licentia provides a further service that is not considered by the others, i.e., it allows to select a license from our dataset and verify whether some selected actions are compatible with such license.
• Functional Description:

  Licentia is a web service application with the aim to support users in licensing data. Our goal is to provide a full suite of services to help in the process of choosing the most suitable license depending on the data to be licensed.

  The core technology used in our services is powered by the SPINdle Reasoner and the use of Defeasible Deontic Logic to reason over the licenses and conditions.

  The dataset of RDF licenses we use in Licentia is the RDF licenses dataset where the Creative Commons Vocabulary and Open Digital Rights Language (ODRL) Ontology are used to express the licenses.

• URL:
  http://­licentia.­inria.­fr/
• Contact:
  Serena Villata
• Participant:
  Cristian Cardellino

7.1.18 Metadatamatic

• Keywords:
  RDF, Semantic Web, Metadata
• Functional Description:
  Website offering a form to generate in RDF the description of an RDF base.
• URL:
  https://­wimmics.­github.­io/­voidmatic/
• Contact:
  Pierre Maillot
• Participants:
  Fabien Gandon, Franck Michel, Olivier Corby, Catherine Faron

7.1.19 MGExplorer

• Name:
  Multivariate Graph Explorer
• Keywords:
  Information visualization, Linked Data
• Scientific Description:
  MGExplorer (Multidimensional Graph Explorer) allows users to explore different perspectives to a dataset by modifying the input graph topology, choosing visualization techniques, arranging the visualization space in meaningful ways to the ongoing analysis and retracing their analytical actions. The tool combines multiple visualization techniques and visual querying while representing provenance information as segments connecting views, which each supports selection operations that help define subsets of the current dataset to be explored by a different view. The adopted exploratory process is based on the concept of chained views to support the incremental exploration of large, multidimensional datasets. Our goal is to provide visual representation of provenance information to enable users to retrace their analytical actions and to discover alternative exploratory paths without loosing information on previous analyses.
• Functional Description:
  MGExplorer is an information visualization tool designed for exploring multivariate graphs, integrating various visualization techniques. It allows users to select and combine these techniques into a graph that traces the exploration path of a database. Developed with the D3.JS library, MGExplorer runs directly in a web browser. The tool is available online and can be customized using SPARQL queries created and managed within the LDViz software, which facilitates the creation, storage, and management of such queries. Additionally, MGExplorer can be integrated into any web project as an npm package, providing a modular solution for data visualization.
• Release Contributions:
  MGExplorer is now available as a web component, making it easy to integrate into any web project via an npm package, accessible at https://www.npmjs.com/package/mgexplorer. It can be customized to visualize either local datasets or results from SPARQL queries.
• URL:
  https://­dataviz.­i3s.­unice.­fr/­mgexplorer
• Publications:
  hal-03292172, hal-03404572, hal-03404580
• Contact:
  Aline Menin
• Participants:
  Aline Menin, Marco Alba Winckler, Olivier Corby
• Partner:
  Universidade Federal do Rio Grande do Sul

7.1.20 Morph-xR2RML

• Name:
  Morph-xR2RML
• Keywords:
  RDF, Semantic Web, LOD - Linked open data, MongoDB, SPARQL
• Functional Description:

  The xR2RML mapping language that enables the description of mappings from relational or non relational databases to RDF. It is an extension of R2RML and RML.

  Morph-xR2RML is an implementation of the xR2RML mapping language, targeted to translate data from the MongoDB database, as well as relational databases (MySQL, PostgreSQL, MonetDB). Two running modes are available: (1) the graph materialization mode creates all possible RDF triples at once, (2) the query rewriting mode translates a SPARQL 1.0 query into a target database query and returns a SPARQL answer. It can run as a SPARQL endpoint or as a stand-alone application.

  Morph-xR2RML was developed by the I3S laboratory as an extension of the Morph-RDB project which is an implementation of R2RML.

• URL:
  https://­github.­com/­frmichel/­morph-xr2rml/
• Publications:
  hal-01207828, hal-01330146, hal-01280951
• Contact:
  Franck Michel

7.1.21 Muvin

• Name:
  Multidimensional Visualization of Networks over Time
• Keywords:
  Data visualization, LOD - Linked open data, Temporal Networks
• Scientific Description:
  Muvin addresses the challenges of visualizing complex collaboration networks by implementing an incremental approach tailored for exploring co-authorship networks composed of multivariate entities distributed over time. Traditional representations of such networks can become visually cluttered, making it difficult to focus on relevant information. To tackle this, Muvin employs a focus+context technique, allowing users to zoom in on specific data points while maintaining an overview of the broader network. By enabling incremental data exploration and supporting multi-layered linked open data (LOD), Muvin effectively handles the complexity and scalability issues of collaboration networks. This approach intends to facilitate domain-specific tasks, such as identifying influential collaborators and understanding knowledge dissemination in co-authorship networks.
• Functional Description:
  Muvin facilitates the exploration of a two-layer network that captures collaborations among entities such as researchers, artists, keywords, and more, as well as the temporal evolution of related elements, including scientific publications or songs. The tool adopts an incremental approach, enabling users to dynamically import data from a SPARQL endpoint into the exploration workflow. SPARQL queries can be created and adjusted on the fly using the LDViz query management tool, allowing users to experiment with different queries to address specific data-related questions. Developed with the D3.js library for visualization, Muvin is designed primarily for exploring data from knowledge graphs. The tool is accessible online at [https://dataviz.i3s.unice.fr/muvin](https://dataviz.i3s.unice.fr/muvin).
• Release Contributions:
  This new version has been generalized to enable the exploration of collaboration networks among all types of entities, based on a wide variety of elements. It also allows the use of data from any SPARQL endpoint through custom queries, prepared directly within the LDViz tool (available at [https://dataviz.i3s.unice.fr/ldviz](https://dataviz.i3s.unice.fr/ldviz)). This flexibility supports addressing specific questions across diverse and varied domains.
• URL:
  http://­dataviz.­i3s.­unice.­fr/­muvin/
• Publication:
  hal-03748134
• Contact:
  Aline Menin
• Participants:
  Aline Menin, Marco Alba Winckler

7.1.22 Olivaw

• Name:
  Ontology Long-lived Integration Via ACIMOV Workflow
• Keywords:
  Ontologies, Ontology engineering, Semantic Web, Git svn, Linked Data, LOD - Linked open data, Web
• Scientific Description:
  Olivaw proposes: (1) command lines that make an Acimov ontology development easier, (2) composite actions that can directly be called in workflows from any Acimov project, (3) a pre-commit hook that prevents mistakes from being pushed to an Acimov repository. The test reports are first represented using the EARL vocabulary and then exported in the markdown format to fit a github environment. A template repository also exists in order for an ontology project to begin with the accurate repository architecture, workflows and special files.
• Functional Description:
  Agile and collaborative approaches to ontology development are crucial because they contribute to making them user-driven, up-to-date, and able to evolve alongside the systems they support, hence proper continuous validation tooling is required to ensure ontologies match these standards all along their development. We propose OLIVAW (Ontology Long-lived Integration Via ACIMOV Workflow), a tool supporting the ACIMOV methodology on GitHub. It relies on W3C Standards to assist the development of modular ontologies through GitHub Composite Actions, pre-commit hooks, or a command line interface. OLIVAW was tested on several ontology projects to ensure its usefulness, genericity and reusability. A template repository is available for a quick start. OLIVAW is published under the LGPL-2.1 license and archived on Software Heritage and Zenodo.
• URL:
  https://­github.­com/­Wimmics/­olivaw
• Publication:
  hal-04823080
• Contact:
  Nicolas Robert
• Partner:
  IMT - MINES Saint-Étienne

7.1.23 PEACE

• Name:
  Providing Explanations and Analysis for Combating Hate Expressions
• Keywords:
  Hate Speech Detection, Generating Explanations, Implicit Hate Speech, Subtle Hate Speech
• Functional Description:

  PEACE is a web tool conceived to support content moderators in exploring and evaluating implicit and subtle hate speech on social media. It comprises three main functionalities: i) the exploratory analysis of hate speech messages characteristics (exploration), ii) the prediction of hatefulness (detection), and iii) the explanation of system predictions (explanation).

  These functionalities incorporate not only a binary classification of whether a message is hateful (including explicit, implicit, and subtle messages), with a detailed explanation in natural language that clarifies why a message is considered hateful and an exploratory analysis of the message characteristics.

• URL:
  https://­3ia-demos.­inria.­fr/­peace/
• Contact:
  Elena Cabrio

7.1.24 plic2owl

• Name:
  Plic2OWL: PlinianCore-to-OWL translation
• Keywords:
  Biodiversity, Semantic Web, Knowledge acquisition, Ontologies
• Functional Description:

  The Plinian Core vocabulary is a standard data model designed to share biological species level information. It is developed as an XML schema (XSD).

  The Plinian Core ontology is a representation the XSD PlinianCore data model as an OWL ontology, to be used in RDF-based knowledge graphs.

  This repository is a Python application that translates the Plinian Core XML schema into an OWL ontology. The output format is RDF Turtle.

• URL:
  https://­github.­com/­Wimmics/­plic2owl
• Contact:
  Franck Michel
• Partners:
  GBIF.ES, Real Jardín Botánico, CSIC

7.1.25 RDFminer

• Keywords:
  Evolutionary Algorithms, Semantic Web, Web API, Dashboard
• Functional Description:
  RDFminer is an open source Web application to automatically discover SHACL shapes through an evolutionary process. It takes an RDF data graph as input, from which shapes are mined and assessed using a probabilistic validation framework. The user can interact with RDFminer through a dashboard where they can launch and monitor the mining of shapes, and analyse the results in real time. Github: https://github.com/Wimmics/RDFminer/
• URL:
  http://­ns.­inria.­fr/­rdfminer
• Publication:
  hal-04566981v1
• Contact:
  Remi Felin
• Participants:
  Remi Felin, Thu Nguyen, Andrea Tettamanzi, Catherine Faron, Fabien Gandon

7.1.26 SciLEX

• Name:
  Science Literature Exploration
• Keywords:
  Textmining, Systematic review, Collaborative science, Linked Data
• Functional Description:
  Scilex is a tool allows to start a scientific paper collect to analyse the state of art of a given domain. It also allows the annotation, the enrichment as well as the analysis of the results.
• Publication:
  hal-04175511
• Contact:
  Celian Ringwald
• Participants:
  Celian Ringwald, Anaïs Ollagnier

7.1.27 SPARQL Micro-services

• Name:
  SPARQL micro-services
• Keywords:
  Web API, RDF, SPARQL, Semantic Web, Knowledge Graphs
• Functional Description:
  The approach leverages the micro-service architectural principles to define the SPARQL Micro-Service architecture, aimed at querying Web APIs using SPARQL. A SPARQL micro-service is a lightweight SPARQL endpoint that typically provides access to a small, resource-centric graph. Furthermore, this architecture can be used to dynamically assign dereferenceable URIs to Web API resources that do not have URIs beforehand, thus literally “bringing” Web APIs into the Web of Data. The implementation supports a large scope of JSON-based Web APIs, may they be RESTful or not.
• Release Contributions:
  Various improvements, updates and bug fixes.
• URL:
  https://­github.­com/­frmichel/­sparql-micro-service
• Publications:
  hal-02060966, hal-01722792, hal-01947589, hal-02168164
• Contact:
  Franck Michel

7.1.28 wam-studio

• Keywords:
  Web Application, Web API, Audio signal processing
• Functional Description:
  WAM Studio is an open source online Digital Audio Workstation (DAW) that takes advantage of a number of APIs and standard W3C technologies, such as Web Audio, WebAssembly, Web Components, Web Midi, Media Devices and more. WAM Studio is also based on the Web Audio Modules (WAM) standard, which was designed to facilitate the development of interoperable audio plug-ins (effects, virtual instruments, virtual piano keyboards as controllers, etc.) - a kind of "VSTs for the Web". DAWs are feature-rich software programs, and therefore particularly complex to develop in terms of design, implementation, performance and ergonomics. Today, the majority of online DAWs are commercial, while the only open source examples lack functionality (no plug-in support, for example) and do not take advantage of the recent possibilities of web browsers (such as WebAssembly). WAM Studio was designed as a technology demonstrator to promote the possibilities offered by recent innovations proposed by the W3C. Developing it was a challenge, as we had to take into account the limitations of sandboxed and constrained environments such as Web browsers, and compensate for latency when we cannot know what hardware is being used, etc.). An online demo and a GitHub repository for the source code are available (https://wam-studio.i3s.univ-cotedazur.fr/).
• Contact:
  Michel Buffa

7.1.29 WebAudio tube guitar amp sims CLEAN, DISTO and METAL MACHINEs

• Name:
  Tube guitar amplifier simulators for Web Browser : CLEAN MACHINE, DISTO MACHINE and METAL MACHINE
• Scientific Description:
  This software is one of the only ones of its kind to work in a web browser. It uses "white box" simulation techniques combined with perceptual approximation methods to provide a quality of guitar playing in hand comparable to the best existing software in the native world.
• Functional Description:
  Software programs for creating real-time simulations of tube guitar amplifiers that behave most faithfully like real hardware amplifiers, and run in a web browser. In addition, the generated simulations can run within web-based digital audio workstations as plug-ins. The "CLEAN MACHINE" version specializes in the simulation of acoustic guitars when playing electric guitars. The DISTO machine specializes in classic rock tube amp simulations, and METAL MACHINE targets metal amp simulations. These programs are one of the results of the ANR WASABI project.
• Release Contributions:
  First stable version, delivered and integrated into the ampedstudio.com software. Two versions have been delivered: a limited free version and a commercial one.
• Publications:
  hal-01721463, hal-01893681, hal-02337828, hal-03087768, hal-01721483, hal-01735478, hal-02366725, hal-02557901, hal-01589330, hal-03087763, hal-01893660, hal-01589229
• Contact:
  Michel Buffa
• Participant:
  Michel Buffa

7.1.30 WheatGenomicsSLKG Visualization Web Application

• Keywords:
  Open Access, Data visualization, Knowledge graph, NLP
• Functional Description:

  The Wheat Genomics Scientific Literature Knowledge Graph (WheatGenomicsSLKG) is a FAIR knowledge graph that exploits the Semantic Web technologies to integrate information about Named Entities (NE) extracted automatically from a corpus of PubMed scientific articles on wheat genetics and genomics.

  The WheatGenomicsSLKG Visualization Web Application is a React and node.js based web application meant to search articles from the WheatGenomicsSLKG using the rich semantics of the reference vocabularies, and provide a visualization of their metadata. This application consists of a frontend and a backend hosted on separate repositories: https://github.com/Wimmics/wheatgenomicsslkg-web-visualization/ https://github.com/Wimmics/wheatgenomicsslkg-web-backend/

• Contact:
  Franck Michel

7.1.31 Zoomathia KG Pipeline

• Name:
  Automatic annotation of an ancient zoological corpus
• Keywords:
  Zoology, NLP, Semantic annotation, Semantic Web
• Functional Description:
  This project provides a text processing pipeline for a corpus of texts on animals compiled within the framework of the Zoomathia GDRI. The web interface allows researchers to explore the corpus via a search for works by concept, explore a selected work while visualizing the concepts annotating each of its parts, and visualize the results of queries implementing competency questions on a selected work from the corpus.
• URL:
  https://­univ-cotedazur.­fr/­recherche-innovation/­structures-de-recherche/­academies-dexcellence/­academie-dexcellence-homme-idees-et-milieux/­projets-de-recherche/­projets-2020-2024/­automazoo-annotation-automatique-dun-corpus-zoologique-ancien
• Contact:
  Catherine Faron
• Partners:
  Université de Nice Sophia Antipolis (UNS), CEPAM (Cultures, Environnements, Préhistoire, Antiquité, Moyen Âge)

CyberAgressionAdo

• Contributors:
  Anaïs Ollagnier, Elena Cabrio, Serena Villata
• Description:
  The CyberAgressionAdo-v1 dataset comprises instances of aggressive multiparty chats in French, gathered through a role-playing game conducted in high schools. This dataset is built upon scenarios that emulate cyber aggression situations prevalent among teenagers, addressing sensitive topics like ethnic origin, religion, or skin color. The recorded conversations have undergone meticulous annotation, taking into account various facets, including participant roles, the occurrence of hate speech, the nature of verbal abuse within the messages, and the identification of humor devices like sarcasm or irony in utterances.
• Dataset PID (DOI,...):
  10.5281/zenodo.14770265
• Project link:
  CyberAgressionAdo-v1, CyberAgressionAdo-V2, CyberAgressionAdo-large
• Publications:
  70
• Contact:
  Anaïs Ollagnier
• Release contributions:
  CyberAgressionAdo-V2 uses a multi-label, fine-grained tagset marking the discursive role of exchanged messages as well as the context in which they occur – for instance, attack (ATK), defend (DFN), counterspeech (CNS), abet/instigate (AIN), gaslight (GSL), etc. The CyberAgressionAdo-Large dataset builds on our previously published work on CyberAgressionAdo, an open-access French dataset created to support research on online hate detection within multiparty conversations. In this extended version, the dataset size has nearly doubled, growing from 19 to 36 aggressive multiparty conversations collected through role-playing simulations in schools. This expansion enables a more in-depth analysis across a broader spectrum of cyber aggression themes.

ElecDeb60to20

• Contributors:
  Serena Villata, Elena Cabrio, Pierpaolo Goffredo
• Description:
  The ElecDeb60to20 dataset is built from the official transcripts of the televised presidential debates in the US from 1960 until 2020, from the website of the Commission on Presidential Debates (CPD). These political debates are manually annotated with argumentative components (claim, premise) and relations (support, attack). In addition, it also includes the annotation of fallacious arguments, based on the following 6 classes of fallacies: ad hominem, appeal to authority, appeal to emotion, false cause, slogan, slippery slope.
• Dataset PID (DOI,...):
  10.18653/v1/2023.emnlp-main.684
• Project link:
  ElecDeb60to20
• Publications:
  117
• Contact:
  Serena Villata
• Release contributions:
  (first release)

TAXREF-LD: Knowledge Graph of the French taxonomic registry

• Contributors:
  Franck Michel, Catherine Faron
• Description:
  TAXREF-LD is a Linked Data knowledge graph representing TAXREF, the French national taxonomical register for fauna, flora and fungus, that covers mainland France and overseas territories. TAXREF-LD is a joint initiative of the UMS Patrinat of the National Museum of Natural History, and the I3S laboratory, University Côte d'Azur, Inria, CNRS.
• Dataset PID (DOI,...):
  DOI:10.5281/zenodo.12733630
• Project link:
  TAXREF-LD, 10.5281/zenodo.12733630
• Publications:
  119
• Contact:
  Franck Michel
• Release contributions:
  version 17.0 implements new SKOS collections and better management of vernacular. See full description at https://github.com/frmichel/taxref-ld/blob/master/CHANGELOG.md

WheatGenomicsSLKG

• Contributors:
  Nadia Yacoubi Ayadi, Franck Michel, Catherine Faron
• Description:
  Wheat Genomics Scientific Literature Knowledge Graph is a FAIR knowledge graph that exploits the Semantic Web technologies to integrate information about Named Entities (NE) extracted automatically from a corpus of PubMed scientific papers on wheat genetics and genomics. This work is supported by the French National Research Agency under grant ANR-18-CE23-0017 (project D2KAB).
• Dataset PID (DOI,...):
  DOI:10.5281/zenodo.10420888
• Project link:
  WheatGenomicsSLKG, 10.5281/zenodo.10420888
• Publications:
  41
• Contact:
  Franck Michel
• Release contributions:
  (first release)

Pharmacogenomics datasets for Ontology Matching

• Contributors:
  Pierre Monnin
• Description:
  These datasets constitute benchmarks to evaluate Ontology Matching algorithms on a complex structure-based instance matching task from the domain of pharmacogenomics. Pharmacogenomics involves $n$-ary tuples representing so-called “pharmacogenomic relationships” and their components of three distinct types: drugs, genetic factors, and phenotypes. The goal resides in matching such tuples. These datasets were extracted from the PGxLOD knowledge graph.
• Dataset PID (DOI,...):
  DOI:10.5281/zenodo.8419361
• Project link:
  PGxLOD, 10.5281/zenodo.8419361
• Contact:
  Pierre Monnin
• Release contributions:
  this is the first published version.

DBpedia.fr : French chapter of the DBpedia knowledge graph dataset

• Contributors:
  Fabien Gandon, Franck Michel, Célian Ringwald,
• Description:
  The DBpedia.fr project ensures the creation and maintenance of a French chapter of the DBpedia knowledge base a crowd-sourced community effort to extract structured content from the information created in various Wikimedia projects. Statistics indicate very high usage rate: the server processed 1.8+ billion queries over the year. This represents a 3.86 million daily average and 32.5 million daily max.
• Dataset PID (DOI,...):
• Project link:
  https://fr.dbpedia.org/
• Contact:
  Célian Ringwald
• Release contributions:
  No new release was done this year but we carried out continuous monitoring and support to ensure a high-availability service.

FALCON: Fallacies in COVID-19 Network-based dataset

• Contributors:
  Mariana Chaves, Elena Cabrio, Serena Villata.
• Description:
  The FALCON dataset is a collection of tweets related to the COVID-19 pandemic and politically associated discussions annotated with 6 fallacy categories: loaded language, appeal to fear, appeal to ridicule, hasty generalization, ad hominem, and false dilemma. Annotations are provided at the tweet level and in a multi-label format, meaning that a tweet can be associated with more than one fallacy category. The dataset includes an underlining graph structure that can be used to model the relationships between the fallacies.
• Dataset PID (DOI,...):
  Not available yet.
• Project link:
  falcon-fallacy-classification
• Publications:
  57
• Contact:
  Mariana Chaves
• Release contributions:
  (first release)

8.1.1 Interaction with extended reality

Participants: Aline Menin, Clément Quéré, Florent Robert, Marco Winckler.

Affordances are crucial tools for supporting interaction in Mixed, Virtual, and Augmented Reality (XR) environments. They define how the system communicates to the user the actions needed to perform a task. Given the lack of consensus and standards in the literature on describing affordances in XR, we explored how affordances are used as a strategy to encourage discovery and engagement within XR environments. We gathered and analyzed studies that explain affordance concepts and conduct experiments in 3D environments, highlighting the affordances applied. Our analysis mapped the use of affordances across eight dimensions: environment type, modality, location, temporal aspect, learning aspect, task category, domain tasks, and affordance type 80.

In particular, Mixed Reality (MR) offers a great potential for annotating physical spaces, allowing users to interact with the real world through digital annotations. Annotations serve various functions, such as providing descriptions, offering assessments, or both, and play a key role in daily life for summarizing and emphasizing content. MR facilitates these annotations by integrating them with the physical environment through head-mounted displays (HMDs), making interactions more seamless.

In fields like real estate, healthcare, and entertainment, MR-driven annotations enhance user experiences, offering immersive, informative, and collaborative benefits. In this context, we proposed and developed an annotation system called HandyNotes, designed to enrich physical objects with semantic information using MR headsets and multiple input methods (audio, gestures, text) 72. To support seamless interaction with the real-world, we proposed an extended hand menu system for intuitive access to tools, an asynchronous note-taking process for sharing annotations. The lessons learned during the development of HandyNotes contribute to more natural and meaningful MR interactions. The tool is currently being enhanced to facilitate data visualization and exploration through annotations in Virtual Reality (VR). Additionally, we aim to simplify the storage, access, and sharing of produced annotations using semantic web technologies, allowing for easy identification of real-world entities and linking them to existing data on the web.

8.1.2 Visual exploration of datasets and models for AI

Participants: Aline Menin, Anaïs Ollagnier.

The rapid expansion of publicly available textual resources, such as lexicons, thesauri, and domain-specific corpora, presents challenges for data practitioners in efficiently identifying the most relevant resources for their tasks. While repositories are emerging to catalog and share these resources, they often lack the advanced search and exploration capabilities users need. Most search methods employ keyword-based queries and/or metadata filtering techniques, which typically return a raw list of possible interesting resources that match the search. This approach is mainly limited by (i) requiring prior knowledge of existing resources to craft effective queries and (ii) failing to reveal potential connections between resources. In response, we present DataLens, a comprehensive web-based platform that integrates faceted search with advanced information visualization techniques to improve resource discovery. Our solution features a filtering-based search, a network-based visualization, and a chained views approach to facilitate data exploration from diverse perspectives. DataLens currently manages a collection of 212,753 resources spanning eight distinct research modalities in machine learning. The tool is available online at DataLens.

8.1.3 Interactive WebAudio applications

Participants: Michel Buffa, Shihong Ren.

During the WASABI ANR research project (2017-2020), we built a 2M song database made of metadata collected from the Web of Data and from the analysis of song lyrics of the audio files provided by Deezer. This dataset is still exploited by current projects inside the team (in particular by the PhD of Maroua Tickat). Other initiatives closely related to the WASABI datasets include several Web Audio interactive applications and frameworks. The Web Audio Modules 2.0, a WebAudio plugin standard for developing high performance plugins in the browser published for the first time in 2021, has encoutered a large adoption by researchers and developers. The open source Wam-Studio Digital Audio Workstation developed by Michel Buffa and Antoine Vidal-Mazuy led to a scientific collaboration with the MERI team from the CCRMA Laboratory in Stanford. The team is also participating to the ANR DOTS project, that aims to produce distributed music performances using Web Audio based infrastructure.

We also developed new methods for real-time tube guitar amplifier simulations that run in the browser. Some of these results are still unique in the world as in 2023, and have been acclaimed by several awards in international conferences. The guitar amp simulations are now commercialized by the CNRS SATT service and are available in the online collaborative Digital Audio Workstation ampedstudio. Some other tools we designed are linked to the WASABI knowledge base, that allow, for example, songs to be played along with sounds similar to those used by artists. An ongoing PhD proposes a visual language for music composers to create instruments and effects linked to the WASABI corpus content and a research collaboration with the Shangai conservatory of Music is also being pursued about the generation of music on the Web with real-time Brain Wave.

More recently, we started some research work on the Musical Metaverse, a concept that refers to an immersive virtual space dedicated to musical activities. It is an extension of the "Metaverse" concept, which defines a set of interconnected virtual worlds where users can interact with each other and with digital objects. We focused on the design of a persistent, real-time multi-participant immersive world for shared music installation creation, exploiting recent W3C web standards such as Web Audio, Web MIDI, WebXR, WebGL, WebGPU, WebAssembly, WebRTC now implemented in the web browsers of the most common VR/XR headsets available on the market. 73, 51, 52, 53, 54, 101, 102.

8.1.4 KartoGraphI: Drawing a Map of Linked Data

Participants: Pierre Maillot, Olivier Corby, Catherine Faron, Fabien Gandon, Franck Michel.

A large number of semantic Web knowledge bases have been developed and published on the Web. To help the user identify the knowledge bases relevant for a given problem, and estimate their usability, we propose a declarative indexing framework and an associated visualization Web application, KartoGraphI. It provides an overview of important characteristics for more than 400 knowledge bases including, for instance, dataset location, SPARQL compatibility level, shared vocabularies, etc. 118

8.3.1 Online Hate Detection in Conversational Data

Participants: Elena Cabrio, Serena Villata, Anais Ollagnier.

Online harassment is prevalent on social networks, and the increasing frequency of anti-social behavior has compelled platform hosts to seek innovative solutions. Most research efforts aimed at addressing online harassment focus on social networks such as Twitter and Instagram. However, recent studies highlight messaging platforms and chat rooms as primary venues for cyberbullying, especially among teenagers. Due to strict data collection policies imposed by major social media platforms, there has been limited research into this phenomenon in multi-party settings. The recent availability of resources simulating online aggression among teens on private messaging platforms has begun to address this gap.

A conference paper presenting a comprehensive study of representation learning methods to address this phenomenon in these contexts is currently under submission. The paper explores various representation learning strategies (including both text- and graph-based methods) and their combinations to tackle multiple hate-related sub-tasks within conversations. This paper makes three key contributions: (1) benchmarking computational models for multi-party dialogue focused on addressing online hate, (2) expanding evaluation considerations for hate-related sub-tasks, and (3) investigating online hate at the linguistic level of pragmatics.

In parallel, we have expanded upon our previously published work on CyberAgressionAdo, an open-access French dataset designed to support research on online hate detection within multiparty conversations. In this extended version, the dataset size has nearly doubled, increasing from 19 to 36 aggressive multiparty conversations collected through role-playing simulations in schools. This expansion facilitates a more comprehensive analysis across a broader range of cyber aggression themes. CyberAgression-Large github URL.

A journal paper consolidating all the methodological protocols for the collection and annotation of these data is currently under publication. The contribution of this paper lies in the significant improvements made to the annotation process, including enhanced guidelines and a two-phase inter-annotator agreement experiment to ensure greater consistency and clarity in labeling. Furthermore, the paper introduces an adaptation of the Weirdness Index to analyze lexical-level disagreements among annotators, offering a novel perspective on understanding divergent interpretations in annotation tasks.

8.3.2 Unveiling the Hate: Generating Faithful and Plausible Explanations for Implicit and Subtle Hate Speech Detection

Participants: Greta Damo, Nicolas Ocampo, Elena Cabrio, Serena Villata.

In today’s digital age, the huge amount of abusive content and hate speech on social media platforms presents a significant challenge. Natural Language Processing (NLP) methods have focused on detecting explicit forms of hate speech, often overlooking more nuanced and implicit instances. To address this gap, our paper aims to enhance the detection and understanding of implicit and subtle hate speech. More precisely, we propose a comprehensive approach combining prompt construction, free-text generation, few-shot learning, and fine-tuning to generate explanations for hate speech classification, with the goal of providing more context for content moderators to unveil the actual nature of a message on social media 59.

8.3.3 PEACE: Providing Explanations and Analysis for Combating Hate Expressions

Participants: Greta Damo, Nicolas Ocampo, Elena Cabrio, Serena Villata.

The increasing presence of hate speech (HS) on social media poses significant societal challenges. While efforts in the Natural Language Processing community have focused on automating the detection of explicit forms of HS, subtler and indirect expressions often go unnoticed. This demo presents PEACE, a novel tool that, besides detecting if a social media message contains explicit or implicit HS, also generates detailed natural language explanations for such predictions. More specifically, PEACE addresses three main challenging tasks: i) exploring the characteristics of HS messages, ii) predicting hatefulness, and iii) elucidating the reasoning behind system predictions. A REST API is also provided to exploit the tool’s functionalities 58.

8.3.4 Is Safer Better? The Impact of Guardrails on the Argumentative Strength of LLMs in Hate Speech Countering

Participants: Helena Bonaldi, Greta Damo, Nicolas Ocampo, Elena Cabrio, Serena Villata.

The potential effectiveness of counterspeech as a hate speech mitigation strategy is attracting increasing interest in the NLG research community, particularly towards the task of automatically producing it. However, automatically generated responses often lack the argumentative richness which characterizes expert-produced counterspeech. In this work, we focus on two aspects of counterspeech generation to produce more cogent responses. First, by investigating the tension between helpfulness and harmlessness of LLMs, we test whether the presence of safety guardrails hinders the quality of the generations. Secondly, we assess whether attacking a specific component of the hate speech results in a more effective argumentative strategy to fight online hate. By conducting an extensive human and automatic evaluation, we show how the presence of safety guardrails can be detrimental also to a task that inherently aims at fostering positive social interactions. Moreover, our results show that attacking a specific component of the hate speech, and in particular its implicit negative stereotype and its hateful parts, leads to higher-quality generations 50.

8.3.5 Argumentation Quality Assessment

Participants: Elena Cabrio, Serena Villata.

We investigated, in 81, the main approaches presented in the literature for the automatic assessment of natural language argumentation. The computational treatment of arguments on controversial issues has been subject to extensive NLP research, due to its envisioned impact on opinion formation, decision making, writing education, and the like. A critical task in any such application is the assessment of an argument’s quality - but it is also particularly challenging. We start from a brief survey of argument quality research, where we identify the diversity of quality notions and the subjectiveness of their perception as the main hurdles towards substantial progress on argument quality assessment. We argue that the capabilities of instruction-following large language models (LLMs) to leverage knowledge across contexts enable a much more reliable assessment. Rather than just fine-tuning LLMs towards leaderboard chasing on assessment tasks, they need to be instructed systematically with argumentation theories and scenarios as well as with ways to solve argument-related problems. We discuss the real-world opportunities and ethical issues emerging thereby.

8.3.6 DISPUTool 2.0: A Modular Architecture for Multi-Layer Argumentative Analysis of Political Debates

Participants: Pierpaolo Goffredo, Elena Cabrio, Serena Villata.

Political debates are one of the most salient moments of an election campaign, where candidates are challenged to discuss the main contemporary and historical issues in a country. These debates represent a natural ground for argumentative analysis, which has always been employed to investigate political discourse structure and strategy in philosophy and linguistics. In this paper, we present DISPUTool 2.0, an automated tool which relies on Argument Mining methods to analyze the political debates from the US presidential campaigns to extract argument components (i.e., premise and claim) and relations (i.e., support and attack), and highlight fallacious arguments. DISPUTool 2.0 allows also for the automatic analysis of a piece of a debate proposed by the user to identify and classify the arguments contained in the text. A REST API is provided to exploit the tool's functionalities 17.

The new version of the DISPUTool demo is publicly accessible at 3ia-demos.inria.fr/disputool/.

8.3.7 Argument-based Detection and Classification of Fallacies in Political Debates

Participants: Pierpaolo Goffredo, Mariana Eugenia Chaves Espinoza, Elena Cabrio, Serena Villata.

Fallacies are arguments that employ faulty reasoning. Given their persuasive and seemingly valid nature, fallacious arguments are often used in political debates. Employing these misleading arguments in politics can have detrimental consequences for society, since they can lead to inaccurate conclusions and invalid inferences from the public opinion and the policymakers. Automatically detecting and classifying fallacious arguments represents therefore a crucial challenge to limit the spread of misleading or manipulative claims and promote a more informed and healthier political discourse. Our contribution to address this challenging task is twofold. First, we extend the ElecDeb60To16 dataset of U.S. presidential debates annotated with fallacious arguments, by incorporating the most recent Trump-Biden presidential debate. We include updated tokenlevel annotations, incorporating argumentative components (i.e., claims and premises), the relations between these components (i.e., support and attack), and six categories of fallacious arguments (i.e., Ad Hominem, Appeal to Authority, Appeal to Emotion, False Cause, Slippery Slope, and Slogans). Second, we perform the twofold task of fallacious argument detection and classification by defining neural network architectures based on Transformers models, combining text, argumentative features, and engineered features. Our results show the advantages of complementing transformer-generated text representations with non-textual features 18.

8.3.8 FALCON: A multi-label graph-based dataset for fallacy classification in the COVID-19 infodemic

Participants: Mariana Eugenia Chaves Espinoza, Elena Cabrio, Serena Villata.

Fallacies are arguments that seem valid but contain logical flaws. During the COVID-19 pandemic, they played a role in spreading misinformation, causing confusion and eroding public trust in health measures. Therefore, there is a critical need for automated tools to identify fallacies in media, which can help mitigate harmful narratives in future health crises. We present two key contributions to address this task. First, we introduce FALCON, a multi-label, graph-based dataset containing COVID-19-related tweets. This dataset includes expert annotations for six fallacy types—loaded language, appeal to fear, appeal to ridicule, hasty generalization, ad hominem, and false dilemma—and allows for the detection of multiple fallacies in a single tweet. The dataset's graph structure enables analysis of the relationships between fallacies and their progression in conversations. Second, we evaluate the performance of language models on this dataset and propose a dual-transformer architecture that integrates engineered features. Beyond model ranking, we conduct statistical analyses to assess the impact of individual features on model performance 57.

8.3.9 Augmenting participation, co-creation, trust and transparency in Deliberative Democracy at all scales through Argument Mining

Participants: Cristian Cardellino, Sofiane Elguendouze, Elena Cabrio, Serena Villata.

In the context of the ORBIS project 1, Argument Mining (AM) holds significant potential to support AI-enhanced democratic deliberation and decision-making. The integration of AM methods into the BCause platform, a “Structured and Decentralised Discussion System for Distributed Decision Making” 2 implied a specific approach to AM, since discourses are structured. BCause data presents a distinct format, where discussions are organized at the statement level. Each statement (i.e., an argumentative sentence articulated by a participant) is either a position (a stance taken on a particular argumentative topic) or an argument that either supports or attacks a given position. This data limitation and the contextual features of BCause prompted a shift towards refining AM models for both argument component detection and relation classification. The classical AM pipeline has been adjusted to focus on what we now refer to as ‘statement-level’ AM. Similar to traditional AM, the process is carried out in two key steps: (1) Statement Classification, where each statement is categorized as either a position, a supporting argument, or an attacking argument, and (2) Statement Relation Classification, where the specific positions targeted by specific supporting or attacking arguments are identified (linked to each other). Further enhancement and refinement of relation classification is achieved through iterative testing within pilot settings, and feedback from both pilot organizations and participants to their deliberative experiments as end-users. In parallel, a more classical AM approach has been experimented 103, revising the model to handle the formats of deliberative discourse to process the pilot data effectively.

8.3.10 Controversy and influence in the Ukraine war: a study of argumentation and counter-argumentation through Artificial Intelligence

Participants: Mariana Eugenia Chaves Espinoza, Sofiane Elguendouze, Elena Cabrio, Serena Villata.

To understand the impact of contreversaries on armed conflicts, in particular the one between Russia and Ukraine, the project CIGAIA3 is focusing on designing and implementing an Artificial Intelligence algorithm for the automatic analysis of argumentation in these controversies in both English and French newspaper articles. This work is based on the joint creation of an annotated dataset from an initial mapping, allowing automatic argumentation analysis to identify and classify controversies. At its current status, the work that has been achieved covers the data crawling and cleaning from the news articles and the preparation of the annotation guidlines to be used for annotating the data with argumentative components on prolific platform4.

8.3.11 Argument-structured Justification Generation for Explainable Fact-checking

Participants: Xiaoou Wang, Elena Cabrio, Serena Villata.

Justification production is a central task in automated fact-checking, and most studies cast this task as summarization. However, the majority of previous studies presume the availability of human-written fact-checking articles, which is unrealistic in practice. In this work, we address this issue by proposing a novel approach to generate argument-based justifications to improve fact-checking. Our contribution is threefold. First, our extensive experimental setting shows that, despite lower ROUGE scores, our argument-structured summarizer produces summaries leading to better claim verification performance than the state-of-the-art summarizer in fact-checking on three different benchmarks for this task. Second, our jointly-trained summarization and evidence retrieval system outperforms the state-of-the-art method on ExClaim, the only dataset where no human-written fact-checking articles are provided during verification of news claims. Third, we show that integrating attackability evaluation into the training process of the summarizer significantly reduces hallucinated argument relations, leading to more reliable and trustworthy justification generation 82.

8.3.12 Study of the Attention Economy, its detrimental impacts and leads for regulation

Participants: Franck Michel, Fabien Gandon.

During the last two decades, leveraging research in psychology, sociology, neuroscience and other domains, Web platforms have brought the process of capturing attention to an unprecedented scale. With the initial commonplace goal of making targeted advertising more effective, the generalization of attention-capturing techniques and their use of cognitive biases and emotions have multiple detrimental side effects such as polarizing opinions, spreading false information and threatening public health, economies and democracies.

Aware of the problems raised and our responsability as a community, since 2023 we have initiated a work meant to warn the computer science community and call for regulation. We brought together contributions from a wide range of disciplines (psychology, sociology, neuroscience, politics, legal domain, computer science, education etc.) to analyze current practices and consequences thereof. We published this work in 2024 at the AI, Ethics and Society conference (AIES) 68 in an article that provides a set of propositions and principles that could be used do drive further works, and to call for actions against these practices competing to capture our attention on the Web.

8.3.13 CasiMedicos-Arg: A Medical Question Answering Dataset Annotated with Explanatory Argumentative Structures

Participants: Ekaterina Sviridova, Elena Cabrio, Serena Villata.

Explaining Artificial Intelligence (AI) decisions is a major challenge nowadays in AI, in particular when applied to sensitive scenarios like medicine and law. However, the need to explain the rationale behind decisions is a main issue also for human-based deliberation as it is important to justify why a certain decision has been taken. Resident medical doctors for instance are required not only to provide a (possibly correct) diagnosis, but also to explain how they reached a certain conclusion. Developing new tools to aid residents to train their explanation skills is therefore a central objective of AI in education. In this paper, we follow this direction, and we present, to the best of our knowledge, the first multilingual dataset for Medical Question Answering where correct and incorrect diagnoses for a clinical case are enriched with a natural language explanation written by doctors. These explanations have been manually annotated with argument components (i.e., premise, claim) and argument relations (i.e., attack, support), resulting in the Multilingual CasiMedicos-Arg dataset which consists of 558 clinical cases in four languages (English, Spanish, French, Italian) with explanations, where we annotated 5021 claims, 2313 premises, 2431 support relations, and 1106 attack relations. We conclude by showing how competitive baselines perform over this challenging dataset for the argument mining task. 79.

8.4.1 Semantic Web for Life Sciences

Participants: Pierre Monnin.

Life sciences produce and consume vast amounts of scientific data. The graph-structured nature of these data naturally leads to data-driven research efforts leveraging Semantic Web and Knowledge Graph technologies. Among such usages, knowledge graph construction and management is a well established topic. One subtask lies in matching similar or related units across datasets to identify possible overlaps. In this direction, this year again, we proposed the track “Pharmacogenomics” in the international challenge “Ontology Alignement Evaluation Initiative”. This track focuses on the matching of pharmacogenomic knowledge units, which are $n$-ary tuples involving components of three distinct types (drugs, genetic factors, and phenotypes). This year again, none of the approaches participating in the 2024 campaign were able to produce alignments. These results highlight once more the interest in considering domain-specific problems, bringing additional challenges to the field of ontology matching. Given the inadequacy of ontology matching systems to produce valid alignments, such challenges are currently unaddressed and require to design new methods or enrich existing ones.

8.4.2 W3C Data activity and AC Rep

Participants: Rémi Ceres, Pierre-Antoine Champin, Fabien Gandon, Franck Michel, Olivier Corby.

Semantic Web technologies are based on a set of standards developed by the World Wide Web consortium (W3C). Participation in these standardization groups gives to researcher the opportunity to promote their results towards a broad audience, and to keep in touch with an international community of experts. Wimmics has a long history of being involved in W3C groups.

As W3C fellow, Pierre-Antoine Champin also works within the W3C team to support Semantic Web related working groups and promote the emergence of new ones, to ensure the necessary evolutions of these technologies. In 2024, the new Linked Web Storage Working Group was chartered, to standardize the Solid protocol. The Solid project was started by Tim Berners-Lee, inventor of the Web, and builds on Semantic Web standards to promote the (re-)decentralization of the Web. Solid has been a research topic for Wimmics in the past years, including in the collaboration with Startin'Blox (see Section 9.1). The RDF-star Working Group is pursuing its efforts to publish the new version of RDF and SPARQL, extending them with the ability to make statements about statements. A new Data Shapes Working Group was created in December 2024 to adapt SHACL to those changes in RDF. We intend to reflect those changes into Corese (see Section 7.1.4); in fact, Corese already implements an experimental version of RDF-star.

Finally, Fabien Gandon remains the W3C AC Rep for Inria representing institute in all standardization processes and W3C meetings (annual W3C TPAC conference and W3C AC Meeting).

8.4.3 AutomaZoo: Automatic annotation of an ancient Zoological Corpus

Participants: Arnaud Barbe, Molka Dhouib, Catherine Faron, Franck Michel.

This activity is part of the HISINUM project funded by the Academy of Excellence 5 of UCAJedi and related to the Zoomathia international research network which aims to study the constitution and transmission of zoological knowledge from Antiquity to the Middle Ages. The aim is to produce a corpus of textual resources semantically annotated by a graph of ancient zoological knowledge, respecting semantic web standards, interoperable and published on the open data web.

In previous steps, we built the ZooKG-Pliny knowledge graph that represents the manual annotations of the ancient zoological text Naturalis Historia (Pliny the Elder). The semantic annotation is done using concepts from the thesaurus TheZoo  120. ZooKG-Pliny allows the integration and the interrogation of relevant knowledge in order to support epistemologists, historians and philologists in their analysis of these texts and knowledge transmission through them  112. We also developed approaches to automatically classify paragraphs into one or more macro collections of concepts (i.e. "Places", "Anthroponym", etc.) from TheZoo  122.

In 2024, we continued the development of the text processing pipeline for a corpus of texts on animals compiled within the framework of the Zoomathia GDRI. The web interface allows researchers to explore the corpus via a search by concept, explore a selected work while visualizing the concepts annotating each of its parts, and visualize the results of queries implementing competency questions on a selected work from the corpus (7.1.31).

8.4.4 A Unified approach to publish semantic annotations of agricultural documents as knowledge graphs

Participants: Nadia Yacoubi Ayadi, Catherine Faron, Franck Michel.

This work was carried out as part of the D2KAB project (Data to Knowledge in Agriculture and Biodiversity), which aims to develop semantic web-based tools to describe and make agronomical data actionable and accessible following the FAIR principles. We focus on constructing domain-specific Knowledge Graphs (KGs) from textual data sources, using Natural Language Processing (NLP) techniques to extract and structure relevant entities. Our approach is based on the formalization of a semantic data model using common linked open vocabularies such as the Web Annotation Ontology (OA) and the Provenance Ontology (PROV). The model was developed by formulating motivating scenarios and competency questions from domain experts. This model has been used to construct three different KGs from three distinct corpora: PubMed scientific publications on wheat and rice genetics and phenotyping, and French agricultural alert bulletins. The named entities to be recognized include genes, phenotypes, traits, genetic markers, taxa and phenological stages normalized using semantic resources such as the Wheat Trait and Phenotype Ontology (WTO), the French Crop Usage (FCU) thesaurus and the Plant Phenological Description Ontology (PPDO). Named entities were extracted using different NLP approaches and tools. The relevance of the semantic model was validated by implementing experts questions as SPARQL queries to be answered on the constructed RDF knowledge graphs. Our work demonstrates how domain-specific vocabularies and systematic querying of KGs can reveal hidden interactions and support agronomists in navigating vast amounts of data. The resources and transformation pipelines developed are publicly available in Git repositories 41).

Leveraging this work, we also contributed to the alignement of descriptions of plants with distinct viewpoints 83.

8.4.5 Semantic Web for Biodiversity

Participants: Franck Michel, Catherine Faron.

This activity addresses the challenges of exploiting knowledge representation and semantic Web technologies to enable data sharing and integration in the biodiversity area.

Through the GBIF CfP Capacity Enhancement Support Programme, we have collaborated with the Museum of Natural History of Paris and GBIF Spain in a joint project to implement the representation of species life traits using the Plinian core vocabulary 121. This entailed the development of a new software (7.1.24) to translate the XSD representation of Plinian Core into an OWL ontology.

8.4.6 Ontology engineering: tooling and methodology

Participants: Fabien Gandon, Nicolas Robert.

We contributed to the Agile and Continuous Integration for Modular Ontologies and Vocabularies (ACIMOV) 63 ontology engineering methodology for developing ontologies and vocabularies. ACIMOV extends the SAMOD agile methodology to (1) ensure alignment to selected reference ontologies; (2) plan module development based on dependencies; (3) define ontology modules that can be specialized for specific domains; (4) empower active collaboration among ontology engineers and domain experts; (5) enable application developers to select views of the ontology for their specific domain and use case. ACIMOV adopts the standard git-based approach for coding, leveraging agility and DevOps principles. It was implemented in OLIVAW using the collaborative software development platforms Github tooled with continuous integration and continuous deployment workflows (CI/CD workflows) that run syntactic and semantic checks on the repository, specialize modules, generate and publish the ontology documentation 111.

8.5.1 Corese Semantic Web Factory

Participants: Rémi Ceres, Fabien Gandon, Olivier Corby.

Corese 113, an open-source Semantic Web platform, implements W3C languages such as RDF, RDFS, OWL RL, SHACL, SPARQL, and extensions including SPARQL Function, SPARQL Transformation, and SPARQL Rule.

In the enhancement of Corese's distribution, two new interfaces, Corese-GUI and Corese-Command, were launched on Flathub. Additionally, a one-click installation script for Corese-Command is now available for Linux and MacOS.

The documentation of Corese has been fully updated and is accessible 5.

The new interface, Corese-Command, supplements existing ones such as Corese-Library, Corese-GUI, Corese-Server, and Corese-Python. Corese-Command, evolving from the previous Corese-CLI, enables command-line usage of Corese. It encompasses subcommands for converting RDF file formats, running SPARQL queries, performing SHACL validation on RDF datasets, and executing SPARQL queries on remote endpoints. Improvements in file loading now allow handling of local files, URLs, or directories.

All interfaces have been unified to support Corese configuration files in properties format.

Enhancements include bug fixes in Corese-Python, addition of Markdown result format for SPARQL, and N-Quads RDF serialization.

Relevant websites include the Corese project site at Corese Web site and the GitHub repository at Corese github URL.

8.5.2 Explanatory Argumentation in Natural Language for Correct and Incorrect Medical Diagnoses

Participants: Benjamin Molinet, Elena Cabrio, Serena Villata.

In the context of the ANTIDOTE project, we investigated the generation of natural language argument-based explanations in medicine 40. A huge amount of research is carried out nowadays in Artificial Intelligence to propose automated ways to analyze medical data with the aim to support doctors in delivering medical diagnoses. However, a main issue of these approaches is the lack of transparency and interpretability of the achieved results, making it hard to employ such methods for educational purposes. It is therefore necessary to develop new frameworks to enhance explainability in these solutions. We present a novel full pipeline to generate automatically natural language explanations for medical diagnoses. The proposed solution starts from a clinical case description associated with a list of correct and incorrect diagnoses and, through the extraction of the relevant symptoms and findings, enriches the information contained in the description with verified medical knowledge from an ontology. Finally, the system returns a pattern-based explanation in natural language which elucidates why the correct (incorrect) diagnosis is the correct (incorrect) one.

8.5.3 ACTA Module Upgrade

Participants: Cristian Cardellino, Theo Alkibiades Collias.

For the ANTIDOTE project, we were in charge of a major refactoring of the original ACTA module 6, enabling the latest Large Language Models (LLM) models from Hugging Face. The new module is a standalone Python Library7 available under Apache License. We are also in the process of refactoring the code for the web application of ACTA to better integrate it with the new modules and writing a code easier to maintain. We have also integrated the new Medical T5, resulting from a collaboration within ANTIDOTE, to the ACTA demo 61. This new version has been published as demo paper at ECAI 2024 55.

8.5.4 RDF Mining

Participants: Ali Ballout, Catherine Faron, Pierre Monnin, Rémi Felin, Andrea Tettamanzi.

The Shapes Constraint Language (SHACL) is a W3C recommendation which allows to represent constraints in RDF, and validate RDF data graphs against these constraints. Acquiring representative and meaningful SHACL constraints from complex and large RDF data graphs is very challenging and tedious. We proposed an approach for the automatic generation of these constraints. It relies on the probabilistic SHACL validation framework to consider the inherent errors in RDF data that we developed in 2023  114. It is based on grammatical evolution (GE) for extracting representative SHACL constraints by mining an RDF data graph 60, 84. We designed RDFminer (7.1.25), an open source Web application to automatically discover SHACL shapes through an evolutionary process. It takes an RDF data graph as input, from which shapes are mined and assessed using a probabilistic validation framework. The user can interact with RDFminer through a dashboard where they can launch and monitor the mining of shapes, and analyze the results in real time. 104. The results of this research line were defended in the PhD thesis of Rémi Felin 13.

The task of evaluating the fitness of a candidate axiom against known facts or data is known as candidate axiom scoring. Being able to accurately score candidate axioms is a prerequisite for automatic schema or ontology induction, but can also be useful for ontology and/or knowledge graph validation. Accurate axiom scoring heuristics are often heavy to compute, which is a big problem if one wants to exploit them in iterative search methods like level-wise generate-and-test or evolutionary algorithms, where large numbers of candidate axioms need to be scored. We have tackled the challenge of learning a predictive model as a surrogate to reasoning, that predicts the acceptability of candidate class axioms, that is fast to execute yet accurate enough to be used in such settings. For this purpose, we have leveraged a semantic similarity measure extracted from the subsumption hierarchy of an ontology and we have proven that our proposed method is able to learn the acceptability labels of candidate OWL class axioms with high accuracy and that it can do so for multiple types of OWL class axioms 48. The results were defended in the PhD thesis of Ali Ballout 94.

8.5.5 Capturing Geospatial Knowledge from Real-Estate Advertisements

Participants: Lucie Cadorel, Andrea Tettamanzi.

In the framework of a CIFRE thesis with Septeo Proptech, we have proposed a workflow to extract geographic and spatial entities based on a BiLSTM-CRF architecture (Bidirectional Long Short-Term Memory Conditional Random Field) with a concatenation of several text representations and to extract spatial relations, to build a structured Geospatial knowledge base. This pipeline has been applied to the case of French housing advertisements, which generally provide information about a property's location and neighborhood. Our results show that the workflow tackles French language and the variability and irregularity of housing advertisements, generalizes Geoparsing to all geographic and spatial terms, and successfully retrieves most of the relationships between entities from the text.

Text representations are widely used in NLP tasks such as text classification. Very powerful models have emerged and been trained on huge corpora for different languages. However, most of the pre-trained models are domain-agnostic and fail on domain-specific data. We performed a comparison of different text representations applied to French Real Estate classified advertisements through several text classification tasks to retrieve some key attributes of a property. Our results demonstrate the limitations of pre-trained models on domain-specific data and small corpora, but also the strength of text representation, in general, to capture underlying knowledge about language and stylistic specificities.

The results of this research line were defended in the PhD thesis of Lucie Cadorel 95.

8.5.6 Outlier Detection in MET data using Subspace Outlier Detection Method

Participants: Dupuy Rony Charles, Andrea Tettamanzi.

In plant breeding, Multi-Environment Field Trials (MET) are commonly used to evaluate genotypes for multiple traits and to estimate their genetic breeding value using Genomic Prediction (GP). The occurrence of outliers in MET is common and is known to have a negative impact on the accuracy of the GP. Therefore, identification of outliers in MET prior to GP analysis can lead to better results. However, Outlier Detection (OD) in MET is often overlooked. Indeed, MET give rise to different level of residuals which favor the presence of swamping and masking effects, where ideal sample points may be portrayed as outliers instead of the true ones. Consequently, without a sensitive and robust outlier detection algorithm, OD can be a waste of time and potentially degrades the accuracy prediction of the GP, especially when the data set is not huge. In this study, we compared various robust outlier methods from different approaches to determine which one is most suitable for identifying MET anomalies. Each method has been tested on eleven real-world MET data sets. Results are validated by injecting a proportion of artificial outliers in each set. The Subspace Outlier Detection Method stands out as the most promising among the tested methods 56.

8.5.7 Estimating User's Knowledge Gain in Search-as-Learning Using Knowledge Graphs

Participants: Andrea Tettamanzi.

In the context of search as learning, users engage in search sessions to fill their information gaps and achieve their learning goals. Tracking the user's state of knowledge is therefore essential for estimating how close they are to achieve these learning goals. In this respect, we extend a recently proposed approach that uses the recognition of entities present in the text to track the user's knowledge. Our approach introduces a more complete representation by considering both the entities and their relations. More precisely, we represent both the user's knowledge and the user's learning goals (or target knowledge) as knowledge graphs. We show that the proposed representation captures a complementary aspect of knowledge, thus helping to improve the user knowledge gain estimation when used in combination with other representations 69.

8.5.8 ISSA: semantic indexing of scientific articles and advanced services

Participants: Anna Bobasheva, Catherine Faron, Aline Menin, Franck Michel, Marco Winckler.

The ISSA 2 project, started in 2023, was completed by the end of 2024. It proposes a generic method to explore the data available in an open archive in order to 1) extract new knowledge, 2) exploit this knowledge with a bibliometric objective and 3) propose services to researchers and documentalists, in particular in terms of bibliometrics and information retrieval. It relies on and extends the outcomes of the ISSA project, in particular the semantic index of the publications of an open archive (metadata, descriptors and named entities mentioned in the text, linked to standard knowledge bases). The proposed methods exploit data mining techniques as well as techniques for the construction, publication and exploitation of knowledge graphs. In addition to Agritrop, CIRAD's open archive that served as a use case in ISSA, ISSA 2 considers the HAL instance of the UR EuroMov Digital Health in Motion.

In 2024, we extended the indexing pipeline (see Section 7.1.14, and 110) to gather additional data about the disciplines and Sustainable Development Goals of each article, and compute the Rao-Stirling diversity index. We also enriched existing interfaces to visualize these new data.

The pipeline and search interface are DOI-identified and available under an open license on public repositories. The knowledge graph produced by the pipeline for the Agritrop archive is also made public as a downloadable dump (DOI: 10.5281/zenodo.10381606) and through a public SPARQL endpoint.

8.5.9 An Open Platform for Quality Measures in a Linked Data Index

Participants: Pierre Maillot, Olivier Corby, Catherine Faron, Fabien Gandon, Franck Michel.

There is a great diversity of RDF datasets publicly available on the web. Choosing among them requires assessing their “fitness for use” for a particular use case, and thus, finding the right quality measures and evaluating data sources according to them. However, this is not an easy task due to the large number of possible quality measures, and the multiplicity of implementation and assessment platforms. Therefore, there is a need for a common way to define measures and evaluate RDF datasets, using open standards and tools.

Developed in the context of the ANR DeKaloG, IndeGx is a SPARQL-based framework to design indexes of Knowledge Graphs declaratively  118. We extended it to support more advanced data quality measures. We demonstrated our approach by reproducing two existing measures, showing how one can formalize and add measures using such an open declarative framework. This work was presented at the Web Conference 2024 66.

8.5.10 Learning Pattern-Based Extractors from Natural Language and Knowledge Graphs: Applying Large Language Models to Wikipedia and Linked Open Data

Participants: Célian Ringwald, Fabien Gandon, Catherine Faron, Franck Michel, Hanna Abi Akl.

Whether automatically extracted from structured elements of articles or manually populated, the open and linked data published in DBpedia, and Wikidata offer rich and structured complementary views of the textual descriptions found in Wikipedia. However, the unstructured text of Wikipedia articles contains a lot of information that is still missing in DBpedia and Wikidata. Extracting them would be interesting to improve the coverage and quality of these knowledge graphs (KG) and this would have an important impact on all downstream tasks.

This work proposes to exploit the dual bases formed from Wikipedia pages and Linked Open Data (LOD) bases covering the same subjects in natural language and in RDF, to produce RDF extractors targeting specific RDF patterns and tuned for a given language. Therefore, the main research question is: Can we learn efficient customized extractors targeting specific RDF patterns from the dual base formed by Wikipedia on one hand, and DBpedia and Wikidata on the other hand?

The landscape of the research field drawn at the intersection of language models and knowledge graphs is very dynamic and quickly evolving. For this reason, as the first step of this work, we designed an extended systematic review of the latest NLP approaches to KG extraction.

In a second step, we started the design a first dataset focused on datatype properties. We restricted the selection of our training to facts respecting a given SHACL shape and information that could be found in the Wikipedia abstract. Then, to learn how to extract relations with datatype properties from natural language, we exploited pre-trained encoder-decoder models, and more precisely BART (denoising autoencoder sequence-to-sequence model). We explored several aspects of the task formulation that could impact the generation of triples in this context: the size of the model, the size of the learning sample needed to learn a given SHACL pattern, and the syntax of the triples 109, 108.

We continued the work by questionning the impact of the syntax chosen for representing the generated output by benchmarking 12 variations of RDF syntaxes, but also by comparing two small langage models (T5 and BART), and demonstrated the performances of a light Turtle syntax 75.

Future works include the systematic extension of the pattern-based relation extraction, as well as the extraction of object properties.

8.5.11 AI agent to convert natural language questions into SPARQL queries

Participants: Franck Michel, Fabien Gandon.

An experimental knowledge graph (KG) driven framework (10.26434/chemrxiv-2023-sljbt) was recently introduced to facilitate the integration of heterogeneous data types, encompassing both experimental data (mass spectrometry annotation, results from biological screening and fractionation) as well as meta-data available on the Web (such as taxonomies and metabolite databases). Although this KG efficiently encapsulates the different data structures and semantic relationships, retrieving specific information through structured or visual queries or even programmatically, is not trivial.

In the collaborative project MetaboT (formerly KG-Bot), we designed and implemented an AI agent that can convert natural language questions into SPARQL queries and programmatic data-mining tasks, and generate adapted visualization. By leveraging the potential of emerging Large Language Models (LLMs) to understand semantic relationships encapsulated in KGs and mentioned in the questions, the agent autonomously iterates to construct a SPARQL query of any submitted natural language question. After retrieving the necessary information from the KG, the agent provides a preliminary interpretation of the results in natural language, along with relevant visualizations and statistics  123.

Following this work, we have submitted an ANR project proposal called MetaboLinkAI. This project was accepted and shall start in 2025.

8.5.12 Hybridizing machine learning and knowledge graphs: injection of relation signatures

Participants: Pierre Monnin.

Knowledge graphs (KGs) are nowadays largely adopted, representing a successful paradigm of how symbolic and transparent AI can scale on the World Wide Web. However, they are generally tackled by Machine Learning (ML) and mostly numeric based methods such as graph embedding models (KGEMs) and deep neural networks (DNNs). The latter methods have been proved efficient but lack major characteristics such as interpretability and explainability. Conversely, these characteristics are intrinsically supported by symbolic AI methods and artefacts, thus motivating a research effort to hybridize machine learning and knowledge graphs.

Towards such an hybridization, we investigated the improvement of KGEMs with symbolic knowledge for the task of link prediction which aims at predicting the missing tail of a triple $(h,r,?)$ or the missing head of a triple $(?,r,t)$. To train such methods, batches of positive and negative triples are considered in loss functions. However, different kinds of negative triples exist: considering signatures of relations (domain and range), some negative triples may be semantically valid (e.g., $(\mathrm{𝙿𝚒𝚎𝚛𝚛𝚎𝙼𝚘𝚗𝚗𝚒𝚗},\mathrm{𝚛𝚎𝚜𝚎𝚊𝚛𝚌𝚑𝚃𝚎𝚊𝚖},\mathrm{𝚆𝚒𝚖𝚖𝚒𝚌𝚜})$), while others may be semantically invalid (e.g., $(\mathrm{𝙿𝚒𝚎𝚛𝚛𝚎𝙼𝚘𝚗𝚗𝚒𝚗},\mathrm{𝚛𝚎𝚜𝚎𝚊𝚛𝚌𝚑𝚃𝚎𝚊𝚖},\mathrm{𝙼𝚎𝚍𝚒𝚝𝚎𝚛𝚛𝚊𝚗𝚎𝚊𝚗𝚂𝚎𝚊})$). We enriched the three main loss functions for link prediction such that all kinds of negatives are sampled but treated differently based on their semantic validity 64, 85. This enrichment led to improved semantic correctness of KGEMs as measured by the Sem@$K$ metric, but also better ranking of gold truth entities as measured by the MRR and Hits@10 metrics. Such results highlight the interest of considering symbolic knowledge in KGEMs.

8.5.13 Enriching benchmark datasets by generating synthetic ontologies and knowledge graphs

Participants: Pierre Monnin.

In tasks of the lifecycle of knowledge graphs (e.g., link prediction, entity classification), only a few KGs established themselves as standard benchmarks for evaluating approaches. However, recent works outline that relying on a limited collection of datasets is not sufficient to assess the generalization capability of an approach. To remedy the aforementioned issues, we released PyGraft, a Python library to generate synthetic ontologies and knowledge graphs by configuring the logical (RDFS and OWL) constructions to use 65, 86. By providing a way of generating both a schema and KG in a single pipeline, this library will support the development a more diverse array of KGs for benchmarking novel approaches. Especially, PyGraft will support the development and evaluation of new neuro-symbolic AI approaches by allowing to integrate and evaluate the contribution of different types of knowledge constructs, thereby going beyond what is currently possible with the limited collection of available benchmarks.

8.5.14 Reusing Wikidata to build new knowledge graphs: the KGPrune platform

Participants: Pierre Monnin.

More and more knowledge graphs are publicly published and accessible on the Web of data, covering a widening array of domains. This allows their reusage in other downstream applications or in the construction of other knowledge graphs. However, not all represented knowledge is useful or pertaining in such cases. This is particularly the case for general large-scale knowledge graphs such as Wikidata. Additionally, the sheer size of such knowledge graphs entails scalability issues. These two aspects ask for efficient methods to extract subgraphs of interest from existing knowledge graphs. To this aim, we introduce KGPrune, an API and Web Application that, given seed entities of interest and properties to traverse, extracts their neighboring subgraphs from Wikidata 107, 43. To avoid topical drift, KGPrune relies on a frugal pruning algorithm based on analogical reasoning to only keep relevant neighbors while pruning irrelevant ones.

8.5.15 Formal Argumentation: How can we understand and deal with implicit arguments?

Participants: Victor David.

Linking Argument Mining and Formal Argumentation to better understand implicit arguments:

Argument mining is a natural language processing technology aimed at identifying arguments in texts. Furthermore, the approach is being developed to identify the premises and claims of those arguments, and to identify the relationships between arguments including support and attack relationships. In the paper 100, we assume that an argument map contains the premises and claims of arguments, and support and attack relationships between them, that have been identified by argument mining. So from a piece of text, we assume an argument map is obtained automatically by natural language processing. However, to understand and to automatically analyze that argument map, it would be desirable to instantiate that argument map with logical arguments. Once we have the logical representation of the arguments in an argument map, we can use automated reasoning to analyze the argumentation (e.g. check consistency of premises, check validity of claims, and check the labelling on each arc corresponds with the logical arguments). We address this need by using classical logic for representing the explicit information in the text, and using default logic for representing the implicit information in the text. In order to investigate our proposal, we consider some specific options for instantiation.

Formal Argumentation to better evaluate the quality of decoding implicit arguments:

An argument can be seen as a pair consisting of a set of premises and a claim supported by them. Arguments used by humans are often enthymemes, i.e., some premises are implicit. To better understand, evaluate, and compare enthymemes, it is essential to decode them, i.e., to find the missing premisses. Many enthymeme decodings are possible. We need to distinguish between reasonable decodings and unreasonable ones. However, there is currently no research in the literature on “How to evaluate decodings?”. To pave the way and achieve this goal, we introduce seven criteria related to decoding, based on different research areas. Then, we introduce the notion of criterion measure, the objective of which is to evaluate a decoding with regard to a certain criterion. Since such measures need to be validated, we introduce several desirable properties for them, called axioms. Another main contribution of the paper 99 is the construction of certain criterion measures that are validated by our axioms. Such measures can be used to identify the best enthymemes decodings.

8.5.16 How to reason with probabilistic and temporal information?

Participants: Victor David, Pierre Monnin.

A new and faster algorithm for reasoning on probabilistic argumentation graphs:

The paper 49 presents fast and exact methods for computing the probability of an argument’s acceptance using Dung’s semantics in the Constellation paradigm of Abstract Argumentation. For (directed) Singly-Connected Graphs (SCGs), the problem can now be solved in linearithmic time instead of being exponential in the number of attacks, as reported in the literature. Moreover, in the more general case of Directed Acyclic Graphs (DAGs), we provide an algorithm whose time complexity is linearithmic in the product of the out-degree of dependent arguments, i.e., arguments reaching the argument considered for acceptance through multiple paths in the graph. We theoretically show that this complexity is lower than the lower-bound of the (exact) Constellation method, which is also supported by empirical results. We also compare our approach on DAGs with the (approximate) Monte-Carlo method, which is stopped when our approach obtains the exact results. Within this time constraint, Monte-Carlo still outputs significant errors, underlying the fast computation of our approach.

A new model able to represent and reason about probabilistically uncertain arguments over a time interval:

The study of Dung-style Argumentation Frameworks in recent years has focused on incorporating time. For example, availability intervals have been added to arguments and relations, resulting in different outputs of Dung semantics over time. The paper 36 examines the probability distribution of arguments over time intervals. Using this temporal probabilistic model, the study explores how these frameworks can be transformed into a probabilistic argumentation according to the constellation approach and how they can be interpreted within the epistemic approach. The epistemic approach relies on the notion of defeat to select significant conflicts based on probability distributions. The study also introduces the temporal acceptability of arguments based on the concept of defence, allowing for more precise results over time. Finally, the models (constellation and epistemic) are extended to account for events that have a duration, i.e., that can occur for several consecutive instants of time.

A Knowledge-Graphs-based approach for extracting the maximal subset of coherent information (i.e., the MAP inference task) from contradictory, uncertain and temporal data:

Reasoning on inconsistent and uncertain data is challenging, especially for Knowledge-Graphs (KG) to abide temporal consistency. Our goal is to enhance inference with more general time interval semantics that specify their validity, as regularly found in historical sciences. We propose a new Temporal Markov Logic Networks (TMLN) model which extends the Markov Logic Networks (MLN) model with uncertain temporal facts and rules. Total and partial temporal (in)consistency relations between sets of temporal formulae are examined. We then propose a new Temporal Parametric Semantics (TPS) which allows combining several sub-functions leading to different assessment strategies. Finally, in 89 we present the NeoMaPy tool, to compute the MAP inference on MLNs and TMLNs with several TPS. We compare our performances with state-of-the-art inference tools and exhibit faster and higher quality results.

CIFRE Contract with Doriane

Participants: Andrea Tettamanzi, Rony Dupuy Charles.

Partner: Doriane.

This collaborative contract for the supervision of a CIFRE doctoral scholarship, relevant to the PhD of Rony-Dupuy Charles, is part of Doriane's Fluidity Project (Generalized Experiment Management), the feasibility phase of which has been approved by the Terralia cluster and financed by the Région Sud-Provence Alpes Côte d'Azur and BPI France in March 2019. The objective of the thesis is to develop machine learning methods for the field of agro-vegetation-environment. To do so, this research work will take into account and address the specificities of the problem, i.e. data with mainly numerical characteristics, scalability of the study object, small data, availability of codified background knowledge, need to take into account the economic stakes of decisions, etc. To enable the exploitation of ontological resources, the combination of symbolic and connective approaches will be studied, among others. Such resources can be used, on the one hand, to enrich the available datasets and, on the other hand, to restrict the search space of predictive models and better target learning methods.

The PhD student developed original methods for the integration of background knowledge in the process of building predictive models and for the explicit consideration of uncertainty in the field of agro-plant environment.

CIFRE Contract with Kinaxia

Participants: Andrea Tettamanzi, Lucie Cadorel.

Partner: Kinaxia.

This thesis project is part of a collaboration with Kinaxia that began in 2017 with the Incertimmo project. The main theme of this project was the consideration of uncertainty for a spatial modeling of real estate values in the city. It involved the computer scientists of the Laboratory and the geographers of the ESPACE Laboratory. It allowed the development of an innovative methodological protocol to create a mapping of real estate values in the city, integrating fine-grained spatiality (the street section), a rigorous treatment of the uncertainty of knowledge, and the fusion of multi-source (with varying degrees of reliability) and multi-scale (parcel, street, neighbourhood) data.

This protocol was applied to the Nice-Côte d'Azur metropolitan area case study, serving as a test bed for application to other metropolitan areas.

The objective of this thesis, which was carried out by Lucie Cadorel under the supervision of Andrea Tettamanzi, was, on the one hand, to study and adapt the application of methods for extracting knowledge from texts (or text mining) to the specific case of real estate ads written in French, before extending them to other languages, and, on the other hand, to develop a methodological framework that makes it possible to detect, explicitly qualify, quantify and, if possible, reduce the uncertainty of the extracted information, in order to make it possible to use it in a processing chain that is finalized for recommendation or decision making, while guaranteeing the reliability of the results.

Plan de Relance with Startin'Blox

Participants: Pierre-Antoine Champin, Fabien Gandon, Maxime Lecoq.

Partner: Startin'Blox.

The subject of this project is to investigate possible solutions to build on top of the Solid architecture capabilities to discover services and access distributed datasets. This would rely on standardized search and filtering capabilities for the Solid PODs, as well as on traversal or federated SPARQL query solving approaches to design a pilot architecture. We also intend to address performance issues via caching or indexing strategies in order to allow a deployment of the Solid ecosystem on a web scale.

An outcome of this collaboration is a vocabulary for describing indexes in the Solid ecosystem. This vocabulary will serve as a starting point for a work item in the W3C Solid Community Group.

CP4SC Project - sub contract

Participants: Fabien Gandon, Rémi Ceres.

Partner: Atos.

Initiated in January 2023, the CP4SC project is a collaborative effort with Atos that focuses on developing a Cloud Platform for Smart Cities. This innovative platform is designed to integrate and analyze data from a wide range of city services and smart devices. As a single, secure access point for data management and dissemination, it promotes innovation and interdepartmental cooperation in urban areas. The project targets sustainable urban development by addressing three key areas: optimizing resource consumption in various living environments through energy management; reducing greenhouse gas emissions via mobility management and alternative transportation solutions; and enhancing environmental conservation and public health through strategic management and observation of the Earth's environment. In that context, Atos has a contract with Wimmics to study the use of semantic technologies and CORESE in managing the data of this Smart City scenario.

10.1.1 Visits of international scientists

10.1.2 Visits to international teams

10.2.1 H2020 projects

10.2.2 Other european programs/initiatives

ANR D2KAB

Participants: Olivier Corby, Catherine Faron, Fabien Gandon, Franck Michel, Nadia Yacoubi Ayadi.

Partners: LIRMM, INRAE, IRD, ACTA

D2KAB is an ANR project which started in June 2019 until June 2024, led by the LIRMM laboratory (UMR 5506). Its general objective is to create a framework to turn agronomy and biodiversity data into knowledge –semantically described, interoperable, actionable, open– and investigate scientific methods and tools to exploit this knowledge for applications in science and agriculture. Within this project the Wimmics team is contributing to the lifting of heterogeneous dataset related to agronomy coming from the different partners of the project and is responsible to develop a unique entry point with semantic querying and navigation services providing a unified view on the lifted data.

Web site: D2KAB Project

ANR DeKaloG

Participants: Olivier Corby, Catherine Faron, Fabien Gandon, Pierre Maillot, Franck Michel.

Partners: Université Nantes, INSA Lyon, Inria Center at Université Côte d'Azur

DeKaloG (Decentralized Knowledge Graphs) is an ANR project until June 2024 that aims to: (1) propose a model to provide fair access policies to KGs without quota while ensuring complete answers to any query. Such property is crucial for enabling web automation, i.e. to allow agents or bots to interact with KGs. Preliminary results on web preemption open such perspective, but scalability issues remain; (2) propose models for capturing different levels of transparency, a method to query them efficiently, and especially, techniques to enable web automation of transparency; (3) propose a sustainable index for achieving the findability principle.

DeKaloG Web site

ANR ATTENTION

Participants: Serena Villata, Elena Cabrio, Xiaoou Wang, Pierpaolo Goffredo.

The ANR project ATTENTION started in January 2022 with Université Paris 1 Sorbonne, CNRS (Centre Maurice Halbwachs), EURECOM, Buster.Ai. The coordinator of the project is CNRS (Laboratoire I3S) in the person of Serena Villata.

In the ATTENTION project, we propose to address the urgent need of designing intelligent semi-automated ways to generate counter-arguments to fight the spread of disinformation online. The idea is to avoid the undesired effects that come with content moderation, such as overblocking , when dealing with disinformation online, and to directly intervene in the discussion (e.g., Twitter threads) with textual arguments that are meant to counter the fake content as soon as possible, and prevent it from further spreading. A counter-argument is a non- aggressive response that offers feedback through fact-bound arguments, and can be considered as the most effective approach to withstand disinformation. Our approach aims at obtaining high quality counter-arguments while reducing efforts and supporting human fact-checkers in their everyday activities.

ANR CIGAIA

Participants: Serena Villata, Mariana Eugenia Chaves Espinoza, Elena Cabrio, Sofiane Elguendouze.

The ANR ASTRID CIGAIA project (December 2022 - 30 Months) "Controversy and influence in the Ukraine war: a study of argumentation and counter-argumentation through Artificial Intelligence" aims to bring together, in a multi-disciplinary way, the research fields of discourse analysis in the humanities and social sciences, with those of automatic extraction of natural language arguments from text (argument mining) in Artificial Intelligence.

Partners are Ecole de l'Air et de l'Espace (EAE), which is also the coordinator of the project, and CNRS (Laboratoire I3S).

ANR CROQUIS

Participants: Andrea Tettamanzi.

The ANR project CROQUIS (March 2022 - 48 months) with CRIL (Lens) and HSM (Montpellier). The coordinator of the project is Salem Benferhat (CRIL). The local coordinator for Laboratoire I3S is Andrea Tettamanzi. The local unit involves two other members of I3S which are not part of WIMMICS, namely Célia da Costa Pereira and Claude Pasquier. The contribution of Wimmics is focused on addressing the problem of incomplete and uncertain data.

Web site: CROQUIS Project

ANR AT2TA

Participants: Pierre Monnin.

Partners: Université de Lorraine (LORIA), Inria Paris (HeKA team), Université Paul Sabatier (IRIT), IHU Imagine, Université Côte d'Azur (I3S), Infologic

The ANR project AT2TA started in February 2023 until February 2026. The coordinator of the project is Miguel Couceiro (LORIA, Université de Lorraine). The local coordinator for I3S / Wimmics is Pierre Monnin. The project aims to develop an analogy-based machine learning framework and to demonstrate its usefulness in real case scenarios. Within the project, the Wimmics team is contributing by investigating the potential usages of analogy-based framewoks with and for knowledge graphs, and the associated adequat representation spaces.

Web site: AT2TA project

ISSA (AAP Collex-Persée)

Participants: Franck Michel, Anna Bobasheva, Olivier Corby, Catherine Faron, Aline Mennin, Marco Winckler.

Partners: CIRAD, Mines d'Alès

The ISSA project started in October 2020 and is led by the CIRAD. It aims to set up a framework for the semantic indexing of scientific publications with thematic and geographic keywords from terminological resources. It also intends to demonstrate the interest of this approach by developing innovative search and visualization services capable of exploiting this semantic index. Agritrop, Cirad's open publications archive, serves as a use case and proof of concept throughout the project. In this context, the primarily semantic resources are the Agrovoc thesaurus, Wikidata and GeoNames.

Wimmics team is responsible for (1) the generation and publication of the knowledge graph representing the indexed entities, and (2) the development of search/visualization tools intended for researchers and/or information.

CROBORA: Crossing Borders Archives: understanding the circulation of images of Europe (ANR)

Participants: Marco Winckler, Aline Menin.

Coordinator: Matteo Treleani, SicLab, Université Côte d'Azur

The CROBORA project (ANR-20-CE38-0002) project led by the Sic.Lab laboratory at EUR CREATES, University of Côte d'Azur, funded by ANR from 2021 to 2024. CROBORA studies the circulation of archive images in the media space. The main hypothesis of the project is that what determines the circulation of archives, thus constituting the visual memory of the European construction, is not a decision that lies solely in the hands of the authors of the reuses (journalists, audiovisual professionals), but rather the consequence of a series of mediations that can be technical (the availability of archives for example), interprofessional (the relationship between archival institutions and the media), cultural (the use of a document for a purpose in one country or another), historical (an archive sequence can change its meaning over time) etc. The general objective of the project is therefore to understand the logics governing the circulation of audiovisual archives. The project aims to respond to the following sub-objectives: (1) to understand which audiovisual fragments are reused in the media to talk about Europe; (2) to build a cartography of frequently used symbolic images; (3) to analyze the representations carried by these images; (4) to understand their trajectory in order to see how they are reshaped diachronically and according to different media, countries and institutions; and finally (5) to identify which mediations determine their readjustments.

Wimmics team is responsible for (i) the development of visualization tools for supporting the exploration of the CROBORA dataset, and (ii) investigating algorithms for optimizing the visual search in the dataset.

CIIAM (Contextual Information Inference for Argument Mining)

Participants: Anaïs Ollagnier.

The CIIAM Project aims to explore the integration of linguistic analysis dimensions related to pragmatics. This approach is particularly innovative, as pragmatics—owing to its complexity and the challenges of formalization—has been largely underexplored from a computational perspective. By utilizing state-of-the-art prompting techniques, the project seeks to address the limitations of existing methods, including challenges such as cultural variability and implicit meaning. The project includes 12 months of funding for a postdoctoral researcher.

Web site: CIIAM Project

KGBot

Participants: Franck Michel, Yousouf Taghzouti, Fabien Gandon.

Partners: Institute of Chemistry of Nice

The KGBot project (Knowledge Graph chatBot) aims to enhance an AI-powered chemistry chatbot prototype designed to improve the accessibility and usability of metabolomics knowledge graphs (KGs). By leveraging mass spectrometry data, the chatbot employs a natural language interface to generate queries (using the SPARQL language), allowing chemists to intuitively explore complex metabolomics knowledge graphs represented in RDF. Key objectives include broadening the chatbot’s compatibility with various large language models (LLMs) and KGs, integrating dynamic tools for data extraction and visualization, and enabling extended dialogical interactions to support iterative queries. The project also seeks to enrich user interactions by providing features such as result visualization, hypothesis generation, and analysis recommendations. Building on the interdisciplinary expertise of the project partners, this initiative fosters transdisciplinary collaboration and aims to deliver scalable solutions applicable across multiple domains. Anticipated outcomes include enhanced access to scientific data and the development of a robust open-source framework to support future academic and industrial applications. Funding will be directed towards supporting postdoctoral researchers and student contributions to the project.

11.1.1 Scientific events: organization

• Organization of The First Workshop on Natural Language Argument-Based Explanations (ArgNLE). Organizers: Elena Cabrio, Rodrigo Agerri, Bernardo Magnini, Marcin Lewinsky, Marie-Francine Moens and Serena Villata. Co-located with the 27th European Conference in Artificial Intelligence. October 20th, 2024.
• Organization of a workshop for the restitution of the results of the ISSA 2 project: “Artificial intelligence at the service of bibliographic research”. Located at Cirad, Montpellier, September 2024. Co-organizer: Franck Michel
• Organization of a workshop on Digital Humanities in the framework of the Hisinum project, September 25th 2024, Maison des Sciences de l'Homme et de la Société Sud-Est. Organizers: Catherine Faron and Arnaud Zucker.
• Organization of the “Journée d'études Extended Reality Research & Creative Center”, third XR2C2 seminar, May 18th 2024, Campus Sophiatech, Sophia Antipolis, France. Co-organizers: Marco Winckler and Aline Menin
• Organization of the “7th IA2 Autumn School” on Artificial Intelligence and Democracy, October 14-18th, 2024, Campus Sophiatech, Sophia Antipolis, France. Co-organizer: Serena Villata, and Victor David

11.1.2 Scientific events: selection

11.1.3 Journal

11.1.4 Invited talks

• Elena Cabrio:
  • “AM-based decision making in the medical and political domains” Keynote speaker at the 1st International Conference on Recent Advances in Robust Argumentation Machines (RATIO-24). Bielefeld, Germany, June 2024.
  • “Analyse automatique de l'argumentation dans les débats politiques”, Collège de France, in the context of B. Sagot's chair on “Apprendre les langues aux machines”. January 2024.
• Catherine Faron:
  • Invited panelist at the plenary meeting of the COST action Distributed Knowledge Graph, Viena, September 2024.
• Fabien Gandon
  • “Knowledge Graphs as the Foundation for Interoperable Intelligent Systems ” at the 6th Knowledge Graph and Semantic Web Conference (KGSWC), December 11-13, 2024, University Paris Cité (France), (slides), 105
  • “Knowledge Graphs: A Pivotal Data Structure for Intelligence”, at workshop ICAIR (Industrial Council on Artificial Intelligence Research), October 2, 2024
• Pierre Monnin
  • Neuro-symbolic approaches for the knowledge graph lifecycle. INESC-ID, Universidade de Lisboa – Seminar of the Language & Speech working group, November 22, 2024, Lisbon, Portugal.
  • Neuro-symbolic approaches for the knowledge graph lifecycle. Università degli Studi di Bari Aldo Moro - Seminar of the PhD Program in Computer Science and Mathematics, January 30, 2024, Bari, Italy.
• Serena Villata
  • Keynote speaker at the 29th International Conference on Natural Language and Information Systems (NLDB-2024), June 2024, Turin, Italy.
  • Keynote speaker at the 10th International Conference on Computational Models of Argument (COMMA-2024), September 2024, Hagen, Germany.
• Anaïs Ollagnier
  • Online Hate Detection in Multi-Party Settings: A Review of Challenges and Solutions. Presented as part of the monthly seminar of the Content-Centered Computing Team. University of Turin, July 4, 2024.
  • Overview of AI: Methodological Foundations and Developments. Presented as part of the 2024 Summer School - Law and AI. Faculty of Law and Political Science, June 4, 2024.
• Marco Winckler
  • "Information Visualization and Analytical Provenance: the missing gap" at the international seminars in relations to Human Computer Interaction, Software Engineering and Accessibility, at KTH Visualization studio, Stockholm, Sweden, June 14th 2024.
  • "Journée dédiée aux technologies immersives et à l'apprentissage", organized by France Immersive Learning, in cooperation with EducAzur and CCI Nice Cote d'Azur, at the Campus Sud des Métiers, Nice, April 3rd 2024. (round table)
  • Inria-Brasil Workshop on AI and Applications. “Contributing to the research in AI and the (Semantic) Web”. Hybrid event physically held at LNCC, Petropolis, Brazil on April 11, 2024.

11.1.5 Scientific expertise

• Elena Cabrio: Member of the Academic Board of University Côte d'Azur, and of the board of Académie 1 IDEX UniCA JEDI.
• Catherine Faron: Member of the HCERES comittee in charge of evaluating Paris Cité 's training offer; Member of the HCERES comittee in charge of evaluating Paris 8's training offer; Member of the HCERES comittee in charge of evaluating the LIASD laboratory; Expert for the European commission, Horizon MSSCA and CL4 programmes.
• Fabien Gandon: European Science Foundation (ESF): Evaluation of an FWO research project.
• Serena Villata: Member of the Bureau of CEP of Inria SAM, Member and vice-chair of the CE23 project evaluation committee of ANR on "Artificial Intelligence", member of the HCERES committee evaluating LTCI Laboratory (IPP), member of the scientific committee of DGFip.
• Marco Winckler: Member of the XRC2 Center for Extended Reality Université Côte d'Azur. Steering Commitee Chair for the IFIP TC13 Conference INTERACT.

11.1.6 Research administration

• Fabien Gandon : Leader of the Wimmics team ; co-president of scientific and pedagogical council of the Data Science Technical Institure (DSTI), W3C Advisory Committee Representative (AC Rep) for Inria.
• Serena Villata: Deputy scientific director of 3IA Côte d'Azur.
• Marco Winckler : Leader of the SPARKS team of the CNRS laboratory I3S (UMR 7271).

11.1.7 Promoting Open Science practices

Too often, the methods described in research papers are not reproducible because the code and/or data are simply not provided. As a result, it is hardly possible to verify the results and build upon these works. The Open Science movement is meant to fix this by fostering the unhindered spreading of the results, methods and products of scientific research. It is based on the open access to publications, data and source codes.

To make the team members aware of these issues, in 2024 we gave a 2-hour presentation on the principles of Open Science, the goals of experiment reproducibility, with a focus on practical approaches meant to make codes and data findable (using metadata), accessible (public repositories and long-time preservation), referenceable (point to a specific version) and citable (give credit, attribution), as well as good practices to cite others' codes and data.

Franck Michel. Open Science, reproducible research, and the citation of articles, code and data alike. 2024. Slides.

11.2.1 Teaching

Participants: Michel Buffa, Elena Cabrio, Olivier Corby, Catherine Faron, Fabien Gandon, Aline Menin, Amaya Nogales Gómez, Andrea Tettamanzi, Serena Villata, Marco Winckler, Molka Dhouib, Benjamin Molinet, Célian Ringwald, Pierre Monnin, Anaïs Ollagnier.

• Michel Buffa:
  • Licence 3, Master 1, Master 2 Méthodes Informatiques Appliquées à la Gestion des Entreprises (MIAGE) : Web Technologies, Web Components, etc. 192h.
  • DS4H Masters 3D games programming on Web, JavaScript Introduction: 40h.
• Olivier Corby:
  • Licence 3 IOTA UniCA 25 hours Semantic Web
  • Licence 3 IA DS4H UniCA 25 hours Semantic Web
• Catherine Faron :
  • Master 2/5A SI PNS: Web of Data, 32 h
  • Master 2/5A SI PNS: Semantic Web 32h
  • Master 2/5A SI PNS: Ingénierie des connaissances 15h
  • Master DSAI UniCA: Web of Data, 30h
  • Master 1/4A SI PNS and Master2 IMAFA/5A MAM PNS: Web languages, 28h
  • Licence 3/3A SI PNS and Master 1/4A MAM PNS: Relational Databases, 60h
  • Master Data ScienceTech Institute (DSTI): Data pipeline, 50h.
• Fabien Gandon :
  • Master: Integrating Semantic Web technologies in Data Science developments, 72 h, M2, Data ScienceTech Institute (DSTI), France.
  • Tutorial Inria Academy, “CORESE and Semantic Web Standards”, 6h, twice : June and December
• Aline Menin :
  • Master 2, Data Visualization, 12h éq. TD (CM/TD), UniCA, MBDS DS4H, France.
  • Polytech 5ème année, UniCA, 13.5h (CM/TP), Data visualization.
  • BUT 2, IUT Nice Côte d'Azur, 160h éq. TD (CM/TD), “Développement efficace”, “Qualité de développement”, and “Développement des Applications avec IHM”.
• Molinet Benjamin:
  • Fabron BUT-1 - Intro NLP - 42h TD.
  • EMSI Casablanca, Master IA2 - Natural Language Processing, 20h CM/TD
  • Master I Computer Science, Text Processing in AI, 2 hours.
• Serena Villata:
  • Master II Droit de la Création et du Numérique - Sorbonne University: Approche de l'Elaboration et du Fonctionnement des Logiciels, 15 hours (CM), 20 students.
  • Master 2 MIAGE IA - University Côte d'Azur: I.A. et Langage : Traitement automatique du langage naturel, 28 hours (CM+TP), 30 students.
  • DUT IA et santé. Natural Language Processing, 4 hours.
• Elena Cabrio:
  • Master 1 Computer Science, Text Processing in AI, 30 hours.
  • Master 2 MIAGE IA: I.A. et Langage : Traitement automatique du langage naturel, 8 hours.
  • Master 1 EUR CREATES, Parcours Linguistique, traitements informatiques du texte et processus cognitifs. Introduction to Computational Linguistics, 30 hours.
  • Master 1 EUR CREATES, Parcours Linguistique, traitements informatiques du texte et processus cognitifs. Textual Data Analysis 30 hours.
  • DUT IA et santé. Natural Language Processing, 2 hours.
  • Licence 2 IUT, Introduction to AI, 30 hours.
  • Licence 1 IUT, Introduction to Database and SQL, 100 hours.
• Andrea Tettamanzi
  • Licence: Introduction à l'Intelligence Artificielle, 45 h ETD, L2, UniCA, France.
  • Master: Logic for AI, 30 h ETD, M1, UniCA, France.
  • Master: Web, 30 h ETD, M1, UniCA, France.
  • Master: Algorithmes Évolutionnaires, 24.5 h ETD, M2, UniCA, France.
  • Master: Modélisation del l'Incertitude, 24.5 h ETD, M2, UniCA, France.
• Marco Winckler
  • Licence 3: Event-driven programming, 45 h ETD, UniCA, Polytech Nice, France.
  • Master 1: Methods and tools for technical and scientific writing, Master DSAI, 15 h ETD, UniCA, DS4H, France.
  • Master 2: Introduction to Scientific Research, 15 h ETD, UniCA, Polytech Nice, France.
  • Master 2: Information Visualisation, 34 h ETD, UniCA, Polytech Nice, France.2024
  • Master 2: Data Visualization, 15 h ETD, UniCA, MBDS DS4H, France.
  • Master 2: Design of Interactive Systems, 34 ETD, UniCA, Polytech Nice, France.
  • Master 2: Evaluation of Interactive Systems, 34 ETD, UniCA, Polytech Nice, France.
  • Master 2: Multimodal Interaction Techniques, 15 ETD, UniCA, Polytech Nice, France.
  • Master 2: Coordination of the TER (Travaux de Fin d'Etude), UniCA, Polytech Nice, France.
  • Master 2: Coordination of the track on Human-Computer Interaction at the Informatics Department, UniCA, Polytech Nice, France.
• Molka Dhouib
  • Licence 3/3A SI PNS: Relational Databases, 32,5h (TD).
  • Master 1/4A SI PNS: Web languages, 10h (TD)
  • Licence 3/LPI: Introduction to Web of Data and Semantic Web, 16h (TD)
• Célian Ringwald:
  • Licence 3/3A SI PNS: Base de données relationnelles, 63,5 h (TD) .
• Pierre Monnin:
  • Master 2/Applied Foreign Languages: Artificial Intelligence, professional applications. 4h CM, 4h TD
  • Master 1/Applied Foreign Languages: Introduction to Artificial Intelligence. 9h CM, 9h TD
  • Master 1/Adult Education: Introduction to Artificial Intelligence. 24h CM
  • Bachelor 1/Preparatory classes for Higher Education: Introduction to Artificial Intelligence. 6h CM
• Anaïs Ollagnier:
  • Master 1/2/Phd EUR LEXSOCIETE. Introduction to AI Applied to Law and Implications for Administration and Public Service. 10h CM
  • Master 1/2/Phd EUR LEXSOCIETE. Introduction to AI Applied to Law. 12h CM, 8h TD
  • Master 1/2/Phd EUR ELMI. Artificial Intelligence and societal tranformation. 12h CM
• Arnaud Barbe:
  • 1ere Année BUT : Introduction aux bases de données relationnelles et SQL, 40h TD.
• Franck Michel:
  • Master 2/5A SI PNS: Web of Data, 16 h

E-learning

• Mooc: Fabien Gandon, Olivier Corby & Catherine Faron, Web of Data and Semantic Web (FR), 7 weeks, FUN, Inria, France Université Numérique, self-paced course 41002, Education for Adults, 17496 learners registered at the time of this report and 855 certificates/badges, MOOC page.
• Mooc: Fabien Gandon, Olivier Corby & Catherine Faron, Introduction to a Web of Linked Data (EN), 4 weeks, FUN, Inria, France Université Numérique, self-paced course 41013, Education for Adults, 5952 learners registered at the time of this report, MOOC page.
• Mooc: Fabien Gandon, Olivier Corby & Catherine Faron, Web of Data (EN), 4 weeks, Coursera, self-paced course Education for Adults, 5134 learners registered at the time of this report, MOOC page.
• Mooc: Michel Buffa, HTML5 coding essentials and best practices, 6 weeks, edX MIT/Harvard, self-paced course Education for Adults, more than 500k learners at the time of this report (2015-2024), MOOC page.
• Mooc: Michel Buffa, HTML5 Apps and Games, 5 weeks, edX MIT/Harvard, self-paced course Education for Adults, more than 150k learners at the time of this report (2015-2024), MOOC page.
• Mooc: Michel Buffa, JavaScript Introduction, 5 weeks, edX MIT/Harvard, self-paced course Education for Adults, more than 250k learners at the time of this report (2015-2024), MOOC page.

11.2.2 Supervision

PhDs

• Defended PhD: Ali Ballout, Active Learning for Axiom Discovery, Supervised by Andrea Tettamanzi, UniCA.
• Defended PhD: Lucie Cadorel, Localisation sur le territoire et prise en compte de l'incertitude lors de l’extraction des caractéristiques de biens immobiliers à partir d'annonces, Supervised by Andrea Tettamanzi, UniCA.
• Defended PhD: Rony Dupuy Charles, Combinaison d'approches symboliques et connexionnistes d'apprentissage automatique pour les nouvelles méthodes de recherche et développement en agro-végétale-environnement, Supervised by Andrea Tettamanzi, UniCA.
• Defended PhD: Rémi Felin, Découverte évolutive d’axiomes à partir de graphes de connaissances, UniCA, Co-supervised by Andrea Tettamanzi, Catherine Faron.
• Defended PhD: Pierpaolo Goffredo, Fallacious Argumentation in Political Debates, UniCA 3IA, Co-supervised by Elena Cabrio and Serena Villata.
• PhD in progress: Guillaume Méroué, Decentralized coordination of intelligent processes to improve the quality of a collection of knowledge graphs, UniCA 3IA, Co-supervised by Pierre Monnin and Fabien Gandon.
• Defended PhD: Benjamin Molinet, Explanatory argument generation for healthcare applications, UniCA 3IA, Co-supervised by Elena Cabrio and Serena Villata.
• PhD in progress: Benjamin Ocampo, Subtle and Implicit Hate Speech Detection, UniCA 3IA, Co-supervised by Elena Cabrio and Serena Villata.
• PhD in progress: Clément Quere. Immersive Visualization Techniques for spatial-temporal data. Co-supervised by Aline Menin, Hui-Yin Wu, and Marco Winckler.
• PhD in progress: Célian Ringwald, Learning RDF pattern extractors for a language from dual bases Wikipedia/LOD, UniCA 3IA, Co-supervised by Fabien Gandon, Catherine Faron, Franck Michel, Hanna Abi-Akl.
• PhD in progress: Nicolas Robert, Knowledge graph embedding models: symbolic knowledge injection and discovery, UniCA, Co-supervised by Catherine Faron and Pierre Monnin.
• Defended PhD: Florent Robert, Analyzing and Understanding Embodied Interactions in Extended Reality Systems. Co-supervised by Hui-Yin Wu, Lucile Sassatelli, and Marco Winckler.
• Defended PhD: Maroua Tikat, Visualisation multimédia interactive pour l’exploration d’une base de métadonnées multidimensionnelle de musiques populaires. Co-supervised by Michel Buffa, Marco Winckler.
• PhD in progress: Xiaoou Wang, Counter-argumentation generation to fight online disinformation, UniCA, Co-supervised by Elena Cabrio and Serena Villata.
• PhD in progress: Greta Damo, Argument-based counter narratives generation to fight online hate speech, UniCA, Co-supervised by Elena Cabrio and Serena Villata.
• PhD in progress: Ekaterina Sviridova, Unveiling Implicit Inferences for Advanced Argument Extraction, UniCA, Co-supervised by Elena Cabrio and Serena Villata.
• PhD in progress: Deborah Dore, Mining arguments over time, UniCA, Co-supervised by Elena Cabrio and Serena Villata.
• PhD in progress: Cyprien Michel-Deletie, Automatic Evaluation of Consistency and Reliability of Information Sources : Toward Deeper Understanding of Discourse with Language Models and Logical Analysis, UniCA, Co-supervised by Elena Cabrio and Serena Villata.

Internships and Apprenticeships

• Apprentice (M2 NumRes) Hajar Bakarou, “Enhancing Fusion Embedding Techniques for Hate Speech Detection in Conversational Data”, Supervised by Anaïs Ollagnier.
• Apprentice (M2 NumRes) Mohamed Sinane El Messoussi, “Infusing Pragmatic Knowledge for Online Hate Detection”, Supervised by Anaïs Ollagnier.
• Apprentice (M1 MIAGE) Erwan Hain, “AI-boosted Deliberation”, Supervised by Elena Cabrio.
• Internship (Polytech, M2) Guillaume Méroué. “Analogical Reasoning for Link Prediction in Knowledge Graphs”. Co-supervised by Pierre Monnin and Fabien Gandon.

Master Projects (TER/PER Projet d'Etude et de Recherches Polytech)

• Master 2 PER, Polytech: Guillaume Méroué. Supervised by Pierre Monnin
• Master 2 Informatique PER + Gratification DS4H: Dheeraj Parkash. “Exploring Signed Network Embedding for Hate Speech Detection on Conversational Data” supervised by Anaïs Ollagnier
• Master 2 Informatique PER + Gratification DS4H: Ahmed Muhammad. “Enhancing Argument Mining through Contextual Information Synthesis” supervised by Anaïs Ollagnier
• Master 2 PER (M2 IA2) Hajar Bakarou, “Enhancing Fusion Embedding Techniques for Hate Speech Detection in Conversational Data”, Supervised by Anaïs Ollagnier.
• Master 2 PER (M2 IA2) Mohamed Sinane El Messoussi, “Exploring Signed Network Embedding for Hate Speech Detection on Conversational Data”, Supervised by Anaïs Ollagnier.
• Master 2 PER (M2 Polytech) Quentin Scordo, “Computing and visualizing innovative bibliometric indicators for the articles of a scientific archive”, Supervised by Franck Michel.
• Master 2 PER (M2 Polytech) Quentin BOURDEAU, Ambre CORREIA et Théo JEANNE, “The Use of Polymorphic Glyphs to Support the Exploration of Spatiotemporal Data”. Co-supervised by Aline Menin and Marco Winckler.
• Master 2 PER (M2 Polytech) Christophe RUIZ and Enzo DAVAL, “Interactive Visualization and Allocation of Office Spaces”. Co-supervised by Aline Menin and Marco Winckler.
• Master 1 PER (M2 DS4H) Steven ESSAM EDWAR AZIZ, “Design and development of a tool for the preservation, archiving, and exhibition of extended reality projects”. Supervised by Aline Menin.

11.2.3 Juries

• Catherine Faron
  • reviewer of the HDR of Sébastien Harispe, Ecole des Mines d'Alès
  • reviewer of the HDR of Lylia Gouaich-Abrouk, Université de Bourgogne
  • reviewer of the PhD thesis of Julian Bruyat, Université de Lyon
  • reviewer of the PhD thesis of Yousouf Taghzouti, Ecole des Mines de Saint Etienne
  • Member of the PhD thesis jury of Mohamed Lechiakh, University Mohammed VI Polytechnic, Morocco
  • President of the PhD jury of Maroua Tikat, Université Côte d'Azur
  • President of the PhD jury of Dupuis Rony Charles, Université Côte d'Azur
  • President of the PhD jury of Benjamin Molinet, Université Côte d'Azur
  • Member of the jury for the PhD prize at the French conference on data management BDA 2024
  • Member of the Nice committee of Inria center at Université Côte d'Azur
  • Member of the I3S laboratory board
• Fabien Gandon
  • President of the jury of the PhD of Ali Ballout on Active Learning for Axiom Discovery
  • President of the jury of the PhD of Pierpaolo Goffredo, Fallacious Argumentation in Political Debates
  • President of the jury of the PhD of Rémi Felin on Découverte évolutive d’axiomes à partir de graphes de connaissances
• Serena Villata
  • Reviewer of the PhD thesis entitled “Knowledge-Enhanced Natural Language Processing” by Giacomo Frisoni, University of Bologna, April 2024.
  • Reviewer of the PhD thesis entitled “Evaluating and Improving the Reasoning Abilities of Language Models” by Chadi Helwé, LIX, June 2024.
  • Reviewer of the PhD thesis entitled “Advancing Fairness in Natural Language Processing: From Traditional Methods to Explainability” by Fanny Jourdan, University of Toulouse, June 2024.
• Elena Cabrio
  • Reviewer of the PhD thesis entitled "Computational approaches to language Change" by Pierluigi Cassotti, University of Bari (Italy), February 2024.
  • Reviewer of the PhD thesis entitled "Boolean Algebra and Random Field Theory applied to Graph Neural Network and Natural Language Processing - Application to Argument Mining in a low resource setting”, by Samuel Guilluy, Rennes, March 2024.
  • Reviewer of the PhD thesis entitled "Summarizing User-generated Discourse" by Shahbaz Syed, University of Leipzig (Germany), March 2024.
  • Reviewer of the PhD thesis entitled "Multimodal Extraction of Proofs and Theorems from the Scientific Literature" by Shrey Mishra, ENS-PSL, June 2024.
  • Reviewer of the PhD thesis entitled "Détection des valeurs humaines dans les commentaires des consommateurs sur les produits parfumés", by Boyu NIU, INALCO Paris, September 2024.
  • Reviewer of the PhD thesis entitled “Generic Framework for the Multidimensional Processing and Analysis of Social Media Content - A Proxemic Approach” by Maxime Masson, University of Pau, September 2024.
  • Reviewer of the PhD thesis entitled "Viewpoints Detection in Political Speeches" by Tu My Doan Norwegian University of Science and Technology, September 2024.
  • Reviewer of the PhD thesis entitled "Improving Trust in Fact-Checking Systems with Synthetic Training Data and Explanations" by Jean-Flavien Bussotti Pitollet, EURECOM, November 2024.
• Marco Winckler
  • Reviewer of the PhD thesis entitled "Acceptabilité de l'intelligence artificielle en context professionnel: Facteurs d'influence et méthodologies d'évaluation" by of Alexandre AGOSSAH. Nantes Université, France. October 9th, 2024.
  • Member of the jury of the PhD thesis entitled "A Framework for Digital Inclusion" by Dena HUSSEIN AL-OMRAN, KTH, Stockholm, Sweden, June 14th, 2024.
  • Member of the jury of the Indiviual Monitoring Commitee (CSI second year) for the PhD thesis entitled "Exploration et analyse interactive de grands graphes de données" by Théo BOUGANIM, Université Paris-Saclay, France, October 15th, 2024.
  • Member of the Recruitement Committee for Associated Professor (MCF 490) at Université Polytech Paris-Saclay, France. Member (rapporteur) of the committee.
  • Member of the Recruitement Committee for Associated Professor Associated Professor (MCF 233) at Université Côte d’Azur, France. Member (rapporteur) of the committee.
  • Member of the Recruitement Committee for Associated Professor Associated Professor (MCF 4880) at Université Paul Sabatier, France. President* of the committee.
  • Member of the Recruitement Committee for Associated Professor Associated Professor (MCF 4925) at IUT Castre/Université Paul Sabatier.
• Aline Menin
  • Invited Member of Maroua Tikat's PhD defense jury. The thesis is entitled Visualisation multimédia interactive pour l’exploration d’une base de métadonnées multidimensionnelle de musiques populaires.

11.3.1 Productions (articles, videos, podcasts, serious games, ...)

• Interview of Fabien Gandon in "Des Initiatives Pour Redonner Confiance en L'IA", Science & Cerveau, September - November 2024, P.80-89
• Interview of Fabien Gandon "Intelligence artificielle : peut-on avoir confiance en elle ?", Sciences et avenir, June 2024

11.3.2 Participation in Live events

• Elena Cabrio: participation at the Science Festival 2024 in Nice, October 2024.
• Serena Villata: participation at the Science Festival 2024 in Antibes, October 2024. Participation to the round table at the Printemps des technologies 2024, March 2024, Centre de Congres Ville Saint Raphael, L'Intelligence Artificielle dans nos vies - dernieres applications.

• Marco Winckler: participation at the "Journée d'accélération de l'ICCARE-Lab : Demain: quel audiovisuel ?", November 29th, 2024, Quartier de la Création, Nantes, France. (round table)

International journals

• 36 articleS.Stefano Bistarelli, V.Victor David, F.Francesco Santini and C.Carlo Taticchi. Temporal Duration-Based Probabilistic Argumentation Frameworks.Journal of Logic and ComputationJuly 2024HALDOIback to text
• 37 articleJ.Julian Bruyat, P.-A.Pierre-Antoine Champin, L.Lionel Médini and F.Frédérique Laforest. PRSC: from PG to RDF and back, using schemas.Semantic Web – Interoperability, Usability, Applicability2024HAL
• 38 articleC. A.Carla Alexandra Martins, C. F.Carina Friedrich Dorneles and M. A.Marco Antônio Winckler. A Comprehensive Review of User Interaction for Recommendation Systems.iSys - Brazilian Journal of Information SystemsDecember 2024HALDOI
• 39 articleA.Aline Menin, C.Clément Quere, J.Jorge Wagner, S.Sonia Chardonnel, P.-A.Paule-Annick Davoine, W.Wolfgang Stuerzlinger, C. M.Carla Maria Dal Sasso Freitas, L.Luciana Nedel and M.Marco Winckler. What about thematic information? An analysis of the multidimensional visualization of individual mobility.Visual InformaticsFebruary 2025. In press. HALDOI
• 40 articleB.Benjamin Molinet, S.Santiago Marro, E.Elena Cabrio and S.Serena Villata. Explanatory argumentation in natural language for correct and incorrect medical diagnoses.Journal of Biomedical Semantics1582024, 8HALDOIback to text
• 41 articleN.Nadia Yacoubi Ayadi, S.Stephan Bernard, R.Robert Bossy, M.Marine Courtin, B. G.Bill Gates Happi Happi, P.Pierre Larmande, F.Franck Michel, C.Claire Nedellec, C.Catherine Roussey and C.Catherine Faron. A Unified approach to publish semantic annotations of agricultural documents as knowledge graphs.Smart Agricultural Technology8January 2024, 43HALDOIback to textback to text

National journals

• 42 articleM.Michel Buffa and A.Antoine Vidal-Mazuy. Une station de travail audio-numérique open-source pour la plate-forme Web.Revue Francophone d'Informatique et Musique1010August 2024HALDOI
• 43 articleP.Pierre Monnin, C.-H.Cherif-Hassan Nousradine, L.Lucas Jarnac, L.Laurel Zuckerman and M.Miguel Couceiro. KGPrune : une application Web pour extraire des sous-graphes d’intérêt de Wikidata par élagage analogique.1024 : Bulletin de la Société Informatique de France24November 2024, 177 - 188HALDOIback to text

International peer-reviewed conferences

• 44 inproceedingsH.Hanna Abi Akl. DSTI at LLMs4OL 2024 Task A: Intrinsic versus extrinsic knowledge for type classification: Applications on WordNet and GeoNames datasets.TIB Open Access Publishing proceedings1st LLMs4OL Challenge @ ISWC 2024Maryland / USA, United StatesOctober 2024HAL
• 45 inproceedingsH. A.Hanna Abi Akl, D.Dominique Mariko, Y.-A.Yann-Alan Pilatte, S.Stéphane Durfort, N.Nesrine Yahiaoui and A.Anubhav Gupta. Knowledge Graphs can play together: Addressing knowledge graph alignment from ontologies in the biomedical domain.KDIR 2024 - 16th International Conference on Knowledge Discovery and Information RetrievalPorto, PortugalNovember 2024HAL
• 46 inproceedingsH. A.Hanna Abi Akl. NeSy is alive and well: A LLM-driven symbolic approach for better code comment data generation and classification.The First International Workshop on Generative Neuro-Symbolic AI (GeNeSy) @ ESWC 2024ESWC 2024 - Extended Semantic Web ConferenceHersonissos, GreeceMay 2024HAL
• 47 inproceedingsH. A.Hanna Abi Akl. Project SHADOW: Symbolic Higher-order Associative Deductive reasoning On Wikidata using LM probing.NATL 2024 - 10th International Conference on Natural Language ComputingMelbourne, AustraliaNovember 2024HAL
• 48 inproceedingsA.Ali Ballout, C.Célia da Costa Pereira and A. G.Andrea G. B. Tettamanzi. Scalable Prediction of Atomic Candidate OWL Class Axioms Using a Vector-Space Dimension Reduced Approach.dblp computer science bibliographyICAART 2024 - 16th International Conference on Agents and Artificial Intelligence316th ICAART 2024, vol 3Rome, ItalySCITEPRESS - Science and Technology Publications2024, 347-357HALDOIback to text
• 49 inproceedingsS.Stefano Bistarelli, V.Victor David, P.Pierre Monnin, F.Francesco Santini and C.Carlo Taticchi. Fast Computing of Dung Semantics in Acyclic Probabilistic Argumentation Frameworks.The 39th Annual AAAI Conference on Artificial Intelligence (AAAI 2025)Thirty-Ninth AAAI Conference on Artificial Intelligence, AAAI 2025Philadelphia, United StatesFebruary 2025HALback to text
• 50 inproceedingsH.Helena Bonaldi, G.Greta Damo, N. B.Nicolás Benjamín Ocampo, E.Elena Cabrio, S.Serena Villata and M.Marco Guerini. Is Safer Better? The Impact of Guardrails on the Argumentative Strength of LLMs in Hate Speech Countering.EMNLP 2024 - 2024 Conference on Empirical Methods in Natural Language ProcessingMiami (Florida), United StatesarXiv2024HALDOIback to text
• 51 inproceedings M.Michel Buffa and S.Samuel Demont. Can you DAW it Online? IS2 2024 - IEEE International Symposium on the Internet of Sounds 2024 / 1st IEEE International Workshop on the Musical Metaverse (IEEE IWMM) Erlangen, Germany September 2024 HAL back to text
• 52 inproceedingsM.Michel Buffa, D.Dorian Girard, S.Samuel Demont, Q.Quentin Escobar and A.Ayoub Hofr. Faust Plugins in (Sometimes Unexpected) Web-Based Hosts.International Faust Conference 2024Turin, ItalyNovember 2024HALback to text
• 53 inproceedingsM.Michel Buffa, A.Ayoub Hofr and D.Dorian Girard. Using Web Audio Modules for Immersive Audio Collaboration in the Musical Metaverse.IS2 2024 - IEEE International Symposium on the Internet of Sounds 2024Erlangen, GermanySeptember 2024HALback to text
• 54 inproceedingsM.Michel Buffa, S.Shihong Ren, T.Tom Burns, A.Antoine Vidal-Mazuy and S.Stéphane Letz. Evolution of the Web Audio Modules Ecosystem.Zenodo, WAC communityWAC 2024 - Web Audio Conference 2024Lafayette, Indiana, United StatesZenodoMarch 2024HALDOIback to text
• 55 inproceedingsC.Cristian Cardellino, T. A.Theo Alkibiades Collias, B.Benjamin Molinet, E.Erwan Hain, W.Wei Sun, R.Rodrigo Agerri, S.Serena Villata and E.Elena Cabrio. ANTIDOTE: ArgumeNtaTIon-Driven explainable artificial intelligence fOr digiTal mEdicine.ECAI 2024 Demos Proceedings - 27th European Conference on Artificial IntelligenceSantiago de Compostela, SpainOctober 2024HALback to text
• 56 inproceedingsD.Dupuy Charles, P.Pascal Pultrini and A. G.Andrea G. B. Tettamanzi. Outlier Detection in MET Data Using Subspace Outlier Detection Method.dblp computer science bibliographyICAART 2024 - 16th International Conference on Agents and Artificial Intelligence16th ICAART 2024: Rome, Italy - Volume 3Rome, ItalySCITEPRESS - Science and Technology PublicationsFebruary 2024, 243-250HALDOIback to text
• 57 inproceedingsM.Mariana Chaves, E.Elena Cabrio and S.Serena Villata. FALCON: A multi-label graph-based dataset for fallacy classification in the COVID-19 infodemic.SAC ’25 - ACM/SIGAPP Symposium on Applied ComputingCatania, Italy2025HALDOIback to textback to text
• 58 inproceedingsG.Greta Damo, N. B.Nicolás Benjamín Ocampo, E.Elena Cabrio and S.Serena Villata. PEACE: Providing Explanations and Analysis for Combating Hate Expressions.ECAI 2024 - 27th European Conference on Artificial IntelligenceSantiago de Compostela, SpainOctober 2024HALback to textback to text
• 59 inproceedingsG.Greta Damo, N. B.Nicolás Benjamín Ocampo, E.Elena Cabrio and S.Serena Villata. Unveiling the Hate: Generating Faithful and Plausible Explanations for Implicit and Subtle Hate Speech Detection.NLDB 2024 - 29th International Conference on Natural Language & Information SystemsTorino, ItalyJune 2024HALback to text
• 60 inproceedingsR.Rémi Felin, P.Pierre Monnin, C.Catherine Faron and A. G.Andrea G. B. Tettamanzi. An Algorithm Based on Grammatical Evolution for Discovering SHACL Constraints.EuroGP 2024 - 27th European Conference on Genetic Programming14631Genetic Programming – 27th European Conference, EuroGP 2024Aberystwyth, United KingdomSpringer Nature Switzerland2024, 176-191HALDOIback to text
• 61 inproceedingsI.Iker García-Ferrero, R.Rodrigo Agerri, A.Aitziber Atutxa, E.Elena Cabrio, I.Iker de la Iglesia, A.Alberto Lavelli, B.Bernardo Magnini, B.Benjamin Molinet, J.Johana Ramirez-Romero, G.German Rigau, J. M.Jose Maria Villa-Gonzalez, S.Serena Villata and A.Andrea Zaninello. Medical mT5: An Open-Source Multilingual Text-to-Text LLM for The Medical Domain.LREC-COLING 2024 - 2024 Joint International Conference on Computational Linguistics, Language Resources and EvaluationTORINO, ItalyMay 2024HALback to text
• 62 inproceedingsM.Matthias Gille Levenson, C.Celian Ringwald, M.Marie Flesch, J.Jennifer Isasi, S.Sofia Papastamkou, R.Riva Quiroga and D.David Valentine. Connecter les chapitres linguistiques de Programming Historian ?: Premières ébauches d'une table conceptuelle multilingue constituée semi-automatiquement.HALHumanistica 2024Sciences de l'informationMeknès, MoroccoMay 2024HAL
• 63 inproceedingsF.-Z. H.Fatma-Zohra Hannou Hannou, V.Victor Charpenay, M.Maxime Lefrançois, C.Catherine Roussey, A.Antoine Zimmermann and F.Fabien Gandon. La méthodologie ACIMOV pour l'intégration agile et continue des modules ontologiques.IC 2024 - 35èmes Journées francophones d'Ingénierie des Connaissances - Plateforme d'intelligence artificielle (PFIA 2024)La Rochelle, FranceJuly 2024, 127-128HALback to text
• 64 inproceedingsN.Nicolas Hubert, P.Pierre Monnin, A.Armelle Brun and D.Davy Monticolo. Treat Different Negatives Differently: Enriching Loss Functions with Domain and Range Constraints for Link Prediction.Lecture Notes in Computer ScienceESWC 2024 - 21st International Conference on Semantic WebSemantic Web - 21st International Conference, ESWC 2024Hersonissos, GreeceMay 2024HALback to textback to text
• 65 inproceedingsN.Nicolas Hubert, P.Pierre Monnin, M.Mathieu D’aquin, D.Davy Monticolo and A.Armelle Brun. PyGraft: Configurable Generation of Synthetic Schemas and Knowledge Graphs at Your Fingertips.Lecture notes in computer scienceESWC 2024 - 21st International Conference on Semantic WebSemantic Web - 21st International Conference, ESWC 2024Hersonissos, GreeceMay 2024HALDOIback to textback to text
• 66 inproceedingsP.Pierre Maillot, J.Jennie Andersen, S.Sylvie Cazalens, C.Catherine Faron, F.Fabien Gandon, P.Philippe Lamarre and F.Franck Michel. An Open Platform for Quality Measures in a Linked Data Index.WWW '24: The ACM Web Conference 2024Singapore, SingaporeACMMay 2024, 1087-1090HALDOIback to text
• 67 inproceedingsC. A.Carla A Martins, C.Carina Dorneles, A.Ankica Barišić, T. R.Thiago Rocha Silva and M.Marco Winckler. CM-DIR: A Method to Support the Specification of the User’s Dynamic Behavior in Recommender Systems.Lecture notes in computer scienceHCSE 2024 - International Conference on Human-Centred Software EngineeringLNCS-14793Human-Centered Software Engineering 10th IFIP WG 13.2 International Working Conference, HCSE 2024, Reykjavik, Iceland, July 8–10, 2024, Proceedings14793Reyjavik, IcelandSpringer2024, 26 - 46HALDOI
• 68 inproceedingsF.Franck Michel and F.Fabien Gandon. Pay Attention: a Call to Regulate the Attention Market and Prevent Algorithmic Emotional Governance.Proceedings of the AAAI/ACM Conference on AI, Ethics, and SocietyAIES 2024 - 7th AAAI/ACM Conference on AI, Ethics, and SocietyVol. 7 (2024): Proceedings of the Seventh AAAI/ACM Conference on AI, Ethics, and Society (AIES-24)7San Jose (CA), United StatesAAAI Press, Washington, DC, USAOctober 2024HALback to text
• 69 inproceedingsH.Hadi Nasser, D.Dima El Zein, C.Célia da Costa Pereira, C.Cathy Escazut and A. G.Andrea G. B. Tettamanzi. RULKKG: Estimating User’s Knowledge Gain in Search-as-Learning Using Knowledge Graphs.ACM Digital LibraryCHIIR 2024 : 2024 ACM SIGIR Conference on Human Information Interaction and RetrievalCHIIR '24: Proceedings of the 2024 Conference on Human Information Interaction and RetrievalSheffield - UK, United KingdomACMMarch 2024, 364-369HALDOIback to text
• 70 inproceedingsA.Anaïs Ollagnier. CyberAgressionAdo-v2: Leveraging Pragmatic-Level Information to Decipher Online Hate in French Multiparty Chats.The 2024 Joint International Conference on Computational Linguistics, Language Resources and EvaluationTorino, ItalyMay 2024HALback to text
• 71 inproceedingsM. A.Mina Abd Nikooie Pour, A.Alsayed Algergawy, E.Eva Blomqvist, P.Patrice Buche, J.Jiaoyan Chen, P. G.Pedro Giesteira Cotovio, A.Adrien Coulet, J.Julien Cufi, H.Hang Dong, D.Daniel Faria, L.Lucas Ferraz, S.Sven Hertling, Y.Yuan He, I.Ian Horrocks, L.Liliana Ibanescu, D. S.Dr Sarika Jain, E.Ernesto Jiménez-Ruiz, N.Naouel Karam, F.Felix Kraus, P.Patrick Lambrix, H.Huanyu Li, Y.Ying Li, P.Pierre Monnin, H.Heiko Paulheim, C.Catia Pesquita, A.Abhisek Sharma, P.Pavel Shvaiko, M.Marta Silva, G.Guilherme Sousa, C.Cassia Trojahn, J.Jana Vataščinová, B.Beyza Yaman, O.Ondrej Zamazal and L.Lu Zhou. Results of the Ontology Alignment Evaluation Initiative 2024.CEUR workshop proceedingsOM 2024 - 19th International Workshop on Ontology Matching (collocated with ISWC-2024)CEUR-3897Proceedings of the 19th International Workshop on Ontology Matching co-located with the 23rd International Semantic Web Conference (ISWC 2024)Baltimore, United States2024, 1-34HAL
• 72 inproceedingsC.Clément Quere, A.Aline Menin, R.Raphaël Julien, H.-Y.Hui-Yin Wu and M.Marco Winckler. HandyNotes: using the hands to create semantic representations of contextually aware real-world objects.IEEE XploreIEEE VR 2024 - The 31st IEEE Conference on Virtual Reality and 3D User InterfacesOrlando, Florida, United StatesMarch 2024HALback to text
• 73 inproceedingsS.Shihong Ren, S.Stéphane Letz, M.Michel Buffa, L.Laurent Pottier and Y.Yang Yu. Design and Run Real-time Spectral Processing on the Web with Faust.ZenodoWAC 2024 - Web Audio Conference 2024Lafayette, Indiana, United StatesZenodoMarch 2024HALDOIback to text
• 74 inproceedingsC.Célian Ringwald, F.Fabien Gandon, C.Catherine Faron, F.Franck Michel and H.Hanna Abi Akl. Well-Written Knowledge Graphs: Most Effective RDF Syntaxes for Triple Linearization in End-to-End Extraction of Relations from Texts (Student Abstract): Well-Written Knowledge Graphs.Proceedings of the 38th AAAI Conference on Artificial IntelligenceAAAI 2024 - 38th Annual AAAI Conference on Artificial Intelligence3821Vancouver, CanadaFebruary 2024, 23631-23632HALDOI
• 75 inproceedingsC.Célian Ringwald, F.Fabien Gandon, C.Catherine Faron, F.Franck Michel and H. A.Hanna Abi Akl. 12 shades of RDF: Impact of Syntaxes on Data Extraction with Language Models.ESWC 2024 Extended Semantic Web ConferenceHersonissos, GreeceMay 2024HALback to textback to text
• 76 inproceedingsC.Celian Ringwald. Learning Pattern-Based Extractors from Natural Language and Knowledge Graphs: Applying Large Language Models to Wikipedia and Linked Open Data.Proceedings of the AAAI Conference on Artificial IntelligenceAAAI-24 - 38th AAAI Conference on Artificial Intelligence38Vol. 38 No. 21: IAAI-24, EAAI-24, AAAI-24 Student Abstracts, Undergraduate Consortium and Demonstrations21Vancouver, CanadaMarch 2024, 23411-23412HALDOI
• 77 inproceedingsF. A.Florent Alain Sauveur Robert, H.-Y.Hui-Yin Wu, L.Lucile Sassatelli and M.Marco Winckler. Task-based methodology to characterise immersive user experience with multivariate data.IEEE VR 2024 - 31st IEEE conference on virtual reality and 3D user interfacesOrlando (FL), United StatesMarch 2024HAL
• 78 inproceedingsS.Shiming Shen, M.Matteo Treleani, A.Aline Menin and M.Marco Winckler. Les Échos visuels: Exploration des Phénomènes de Répétition dans les Archives audiovisuelles.HALHumanistica 2024Sciences de l'informationMeknès, MoroccoMay 2024HAL
• 79 inproceedingsE.Ekaterina Sviridova, A.Anar Yeginbergen, A.Ainara Estarrona, E.Elena Cabrio, S.Serena Villata and R.Rodrigo Agerri. CasiMedicos-Arg: A Medical Question Answering Dataset Annotated with Explanatory Argumentative Structures.ACL AnthologyEMNLP 2024 - Conference on Empirical Methods in Natural Language ProcessingProceedings of the 2024 Conference on Empirical Methods in Natural Language ProcessingMiami, United StatesAssociation for Computational LinguisticsNovember 2024, 18463-18475HALDOIback to text
• 80 inproceedingsV.Victor Vieira, E.Eder Oliveira, A.Aline Menin, E.Esteban Clua, M.Marco Winckler and D.Daniela Trevisan. Understanding affordances in XR interactions through a design space.ACM Digital LibraryIHC 2024 - XXIII Brazilian Symposium on Human Factors in Computing Systems2024-10-11IHC '24: Proceedings of the XXIII Brazilian Symposium on Human Factors in Computing SystemsBrasília DF Brazil, FranceACMOctober 2024, 1 - 14HALDOIback to text
• 81 inproceedingsH.Henning Wachsmuth, G.Gabriella Lapesa, E.Elena Cabrio, A.Anne Lauscher, J.Joonsuk Park, E. M.Eva Maria Vecchi, S.Serena Villata and T.Timon Ziegenbein. Argument Quality Assessment in the Age of Instruction-Following Large Language Models.ACL AnthologyLREC/COLING 2024 - Joint International Conference on Computational Linguistics, Language Resources and Evaluation, LREC/COLING 2024Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024)Torino, ItalyMay 2024HALback to text
• 82 inproceedingsX.Xiaoou Wang, E.Elena Cabrio and S.Serena Villata. Argument-structured Justification Generation for Explainable Fact-checking.IEEE XploreWI-IAT 2024 - 23rd IEEE/WIC International Conference on Web Intelligence and Intelligent Agent TechnologyBangkok, ThailandDecember 2024HALback to text

National peer-reviewed Conferences

• 83 inproceedingsF.Florence Amardeilh, S.Sophie Aubin, S.S Bernard, S.Sonia Bravo, R.Robert Bossy, C.Catherine Faron, F.F Michel and C.Catherine Roussey. Aligner les descriptions des plantes ayant des points de vue distincts.IC2024 : 35es Journées francophones d'Ingénierie des Connaissances35es Journées francophones d'Ingénierie des Connaissances (IC 2024) @ Plate-Forme Intelligence Artificielle (PFIA 2024)ICPlate-Forme Intelligence Artificielle (PFIA)2024La Rochelle, FranceAFIA-Association Française pour l'Intelligence ArtificielleJuly 2024, 121-122HALDOIback to text
• 84 inproceedingsR.Rémi Felin, P.Pierre Monnin, C.Catherine Faron and A. G.Andrea G. B. Tettamanzi. Extraction probabiliste de formes SHACL à l'aide d'algorithmes évolutionnaires.Revue des Nouvelles Technologies de l'InformationEGC 2024 - Extraction et Gestion de la ConnaissanceRNTI-E-40Dijon, France2024HALback to text
• 85 inproceedingsN.Nicolas Hubert, P.Pierre Monnin, A.Armelle Brun and D.Davy Monticolo. Enrichissement de fonctions de perte avec contraintes de domaine et co-domaine pour la prédiction de liens dans les graphes de connaissance.Actes de la 27e Conférence Nationale en Intelligence Artificielle27e Conférence Nationale en Intelligence ArtificielleLa Rochelle, FranceJuly 2024HALback to text
• 86 inproceedingsN.Nicolas Hubert, P.Pierre Monnin, M.Mathieu D’aquin, D.Davy Monticolo and A.Armelle Brun. PyGraft: un outil Python pour la génération de schémas et graphes de connaissance synthétiques.35es Journées francophones d'Ingénierie des Connaissances (IC 2024) @ Plate-Forme Intelligence Artificielle (PFIA 2024)IC2024 : 35es Journées francophones d'Ingénierie des ConnaissancesLa Rochelle, FranceJuly 2024HALback to text
• 87 inproceedingsS.Sarra Ouelhadj, P.-A.Pierre-Antoine Champin and J.Jérémy Gaillard. sETL: Outils ETL pour la construction de graphes de connaissances en exploitant la sémantique implicite des schémas de données.Journées francophones d'Ingénierie des Connaissances (IC 2024) @ Plate-Forme Intelligence Artificielle (PFIA 2024)IC20 2024 - 35èmes journées francophones d’Ingénierie des Connaissances. Événement affilié à PFIA 2024 - Plate-Forme Intelligence ArtificielleIC2024 : 35es Journées francophones d'Ingénierie des ConnaissancesLa Rochelle, FranceJuly 2024HAL
• 88 inproceedingsM.Molka Tounsi Dhouib, E.Ekaterina Kostrykina and C.Catherine Faron. Automatic definition of the level of textual difficulty of documents.Revue des Nouvelles Technologies de l'Information24ème conférence francophone sur l'Extraction et la Gestion des ConnaissancesDijon, France2024HAL

Conferences without proceedings

• 89 inproceedingsV.Victor David, R.Raphaël Fournier-S 'Niehotta and N.Nicolas Travers. MAP Inference Reasoning on TMLN with Neo4j.BDA'24Orléans, FranceOctober 2024HALback to text
• 90 inproceedingsJ.Jeanne Ferrari-Giovanangeli, M.Matteo Treleani and A.Aline Menin. ILIADE – Héritage immersif: Les enjeux des standards et de l’institutionnalisation manquée.Journées thématiques Arts et Humanités 2024Nice, FranceMarch 2024HAL

Edition (books, proceedings, special issue of a journal)

• 91 periodicalM.Miguel Couceiro, E.Esteban Marquer, P.Pierre Monnin and P.-A.Pierre-Alexandre Murena, eds. Preface to the special issue on analogies: from mathematical foundations to applications and interactions with ML and AI.Annals of Mathematics and Artificial IntelligenceDecember 2024HALDOI
• 92 periodicalC.Catherine Faron and S.Sabine Loudcher, eds. Special issue on Advances in Knowledge Discovery and Management, Best Papers of EGC 2023..Data and Knowledge Engineering154Special issueDecember 2024, 102376HAL
• 93 proceedingsEngineering Interactive Computer Systems. EICS 2023 International Workshops and Doctoral Consortium : Swansea, UK, June 26-27, 2023, Selected Papers.EICS 2023 - 15th ACM SIGCHI Symposium on Engineering Interactive Computing SystemsLNCS-14517Lecture Notes in Computer ScienceSpringer Nature Switzerland2024, I--XIV, 1--224HALDOI

Doctoral dissertations and habilitation theses

• 94 thesisA.Ali Ballout. Active learning for axiom discovery.Université Côte d'AzurJune 2024HALback to text
• 95 thesisL.Lucie Cadorel. Qualifying and quantifying uncertainty of geolocation information extracted from french real estated ads.Université Côte d'AzurJanuary 2024HALback to text
• 96 thesisB.Benjamin Molinet. Argument-based natural language explanation generation and assessment in healthcare.Université Côte d'AzurDecember 2024HAL
• 97 thesisF.Florent Robert. Analyzing and understanding embodied interactions in virtual reality systems.Université Côte d'AzurDecember 2024HAL
• 98 thesisM.Maroua Tikat. Contributing to the interactive annotation of multi-dimensional knowledge graphs : a case study of popular music data.Université Côte d'AzurSeptember 2024HAL

Reports & preprints

• 99 miscJ.Jonathan Ben-Naim, V.Victor David and A.Anthony Hunter. An Axiomatic Study of the Evaluation of Enthymeme Decoding in Weighted Structured Argumentation.November 2024HALback to text
• 100 miscJ.Jonathan Ben-Naim, V.Victor David and A.Anthony Hunter. Understanding Enthymemes in Argument Maps: Bridging Argument Mining and Logic-based Argumentation.August 2024HALback to text

Other scientific publications

• 101 inproceedingsM.Michel Buffa and S.Samuel Demont. DAW it again! An Audio Workstation for the Web.IS2 2024 - IEEE International Symposium on the Internet of Sounds 2024Erlangen, GermanySeptember 2024HALback to text
• 102 inproceedingsM.Michel Buffa, A.Ayoub Hofr and D.Dorian Girard. WAM Jam Party: Using Web Audio Modules in the Musical Metaverse.IS2 2024 - IEEE International Symposium on the Internet of Sounds 2024 / 1st IEEE International Workshop on the Musical Metaverse (IEEE IWMM)Erlangen, GermanySeptember 2024HALback to text
• 103 inproceedingsC.Cristian Cardellino, S.Serena Villata and E.Elena Cabrio. From Political Debates to Deliberative Democracy: A Roadmap to Assess Semi-Supervised Argument Mining with DISPUTool.DELITE 2024T - he First Workshop on Language-driven Deliberation TechnologyTorino, ItalyMay 2024HALback to text
• 104 inproceedingsR.Rémi Felin, P.Pierre Monnin, C.Catherine Faron and A. G.Andrea G. B. Tettamanzi. RDFminer: an Interactive Tool for the Evolutionary Discovery of SHACL Shapes.ESWC 2024 - 21st International Conference on Semantic WebHersonissos (Crete), GreeceMay 2024HALback to text
• 105 miscF.Fabien Gandon. Knowledge Graphs as the Foundation for Interoperable Intelligent Systems: Keynote Fabien Gandon KGSWC 2024.Université Paris Cité, FranceDecember 2024HALback to text
• 106 inproceedingsF.Frederic Metereau, F.Franck Michel, P.PIERRE LARMANDE, G.Guilhem Sempere and C.Catherine Faron. Integration of variation data through SPARQL Micro-Services.Semantic Web for Health Care and Life Science (SWA4HCLS)Leiden (DE), NetherlandsFebruary 2024HAL
• 107 inproceedingsP.Pierre Monnin, C.-H.Cherif-Hassan Nousradine, L.Lucas Jarnac, L.Laurel Zuckerman and M.Miguel Couceiro. KGPrune: a Web Application to Extract Subgraphs of Interest from Wikidata with Analogical Pruning.ECAI 2024 - 27th European Conference on Artificial IntelligenceECAI 2024 - 27th European Conference on Artificial Intelligence, October 19-24, 2024, Santiago de Compostela, SpainSantiago de Compostela, SpainIOS PressOctober 2024HALDOIback to text
• 108 inproceedingsC.Celian Ringwald, F.Fabien Gandon, C.Catherine Faron, F.Franck Michel and H. A.Hanna Abi Akl. Learning Pattern-Based Extractors from Natural Language and Knowledge Graphs Applying Large Language Models to Wikipedia & the Linked Open Data (POSTER).AAAI 2024 - 38th Annual AAAI Conference on Artificial IntelligenceVancouver, FranceFebruary 2024HALback to text
• 109 inproceedingsC.Celian Ringwald, F.Fabien Gandon, C.Catherine Faron, F.Franck Michel and H. A.Hanna Abi Akl. Well-written Knowledge Graphs Most Effective RDF Syntaxes for Triple Linearization in End-to-End Extraction of Relations from Text (Student Abstract).AAAI 24 - 38th Annual AAAI Conference on Artificial IntelligenceVancouver, CanadaFebruary 2024HALback to text

Software

• 110 softwareA.Anna Bobasheva, F.Franck Michel, A.Andon Tchechmedjiev and A.Anne Toulet. ISSA Pipeline.2.1.0November 2024Inria & Université Cote d'Azur, CNRS, I3S, Sophia Antipolis, France; Cirad; Euromov Digital Health in Motion, IMT Mines Alès lic: Apache License 2.0.HALDOISoftware HeritageVCSback to text
• 111 softwareN.Nicolas Robert, F.Fabien Gandon and M.Maxime Lefrançois. olivaw.0.0.7December 2024 lic: https://spdx.org/licenses/LGPL-2.1.HALDOISoftware HeritageVCSback to text