BPI funded project : AZKAR

Participants : Alain Giboin, Thierry Bergeron, Michel Buffa, Catherine Faron-Zucker.

AZKAR is a two years French project funded by BPI (Banque Publique d'Investissement), focused on Fast Control of Mobile Robots over the Internet, using Web technologies such as WebRTC and semantic Web technologies. The project started September 15th 2014. The first step of the project will be the evaluation/benchmarking of video and data solutions over internet, based on the WebRTC technology. The second step will consist in helping the robotic partner in the project (the Robosoft company) to implement these solutions on a real mobile robot that will be deployed in museums or in homes for helping seniors in their daily tasks. Semantic Web technologies, will be used in the project for describing the services, the context of the application domain, the content transmitted, etc.

This year, Wimmics main contributions were: a state-of-the-art on the techniques for transferring Web-based data/audio/video ; prototypes based on the technologies selected from the state-of-the-art ; a procedure and quantitative and qualitative criteria for benchmarking the prototypes.

ANR LabCom SMILK

Participants : Farhad Nooralahzadeh, Elena Cabrio, Fabien Gandon.

SMILK (Social Media Intelligence and Linked Knowledge) is a joint laboratory (LabCom, 2013-2016) between the Wimmics team and the Research and Innovation unit of VISEO (Grenoble). Natural Language Processing, Linked Open Data and Social Networks as well as the links between them are at the core of this LabCom. The purpose of SMILK is both to develop research and technologies in order to retrieve, analyze, and reason on textual data coming from Web sources, and to make use of LOD, social networks structures and interaction in order to improve the analysis and understanding of textual resources. Topics covered by SMILK include: use of data and vocabularies published on the Web in order to search, analyze, disambiguate and structure textual knowledge in a smart way, but also to feed internal information sources; reasoning on the combination of internal and public data and schemes, query and presentation of data and inferences in natural formats.

Ministry of Culture: DBpedia.fr

Participants : Raphaël Boyer, Fabien Gandon.

This project named "DBpedia.fr" proposes the creation of a French chapter of the base DBpedia used in many English applications, in particular for the publication of cultural collections. Because DBpedia is focused on the English version of Wikipedia it ignores some of the French topics and their data. This project aims at extracting a maximum of RDF data from the French version and providing a stable and scalable end-point for them. We now consider means to improve both the quantity and the quality of the data. The DBpedia.fr project was the first project of the Semanticpedia convention signed by the Ministry of Culture, the Wikimedia foundation and Inria.

A new complete DBpedia extraction has been performed, together with a technical documentation to reproduce it and a documentation for the users has been done too. In addition we have included the last community user interface and adapted it for French DBpedia. This version is more ergonomic and detailed, but also integrates a new SPARQL editor named Flint for students and beginners. A new DBpedia service from the community has been adapted for the French version: it's called "fragments", a service made for minimizing server processing.

Some scripts have been developed, one for generation of statistics based on log, others for grouping the abstracts of each language, based on redirections and interlanguages linked data. Also to increase our amount of available data, we created a new extractor that can extract historic and make statistics of modifications of each Wikipedia article.

Ministry of Culture: GT 6

Participant : Fabien Gandon.

We supervised the working group GT6 Ministry of Culture on the creation of a research convention to foster research and development at the crossroad of culture and digital sciences.

ANR OCKTOPUS

Participants : Fabien Gandon, Catherine Faron-Zucker, Zide Meng.

OCKTOPUS is an ANR project (2012-2016). The objective of OCKTOPUS is to increase the potential social and economic benefit of the large and quickly growing amounts of user-generated content, by transforming it into useful knowledge. We believe that it is possible to considerably improve upon existing generic Information Retrieval techniques by exploiting the specific structure of this content and of the online communities which produce it. Specifically, we will focus on a multi-disciplinary approach in order to address the problem of finding relevant answers to questions within forums and question-answer sites. To create metrics and predictors of content quality and use them to improve the search experience of a user, we will take advantage of:

GDRI Zoomathia

Participants : Olivier Corby, Catherine Faron-Zucker, Alexandre Monnin, Andrea Tettamanzi.

Wimmics is partner of International Research Group (GDRI) Zoomathia funded by two CNRS institutes: INEE and INSHS. It aims at studying transmission of zoological knowledge from Antiquity to Middle-Age through material resources (bio residues, artefacts), iconography and texts.

One of the goals of the project is to design a thesaurus and semantically annotate resources, capturing different types of knowledge: zoonyme, historical period, zoological speciality (ethology, anatomy, physiology, psychology, zootechnique, etc.), litterary genre or iconography.

We started to work on 1) the translation of manual annotations of middle-age structured texts from XML to RDF, 2) the automatic extraction of RDF annotations from text using NLP techniques and 3) the exploitation of these semantic metadata to help historians in their studies of knowledge transmission through these texts.

Semantic EDUCLOUD Carnot Project

Participants : Oscar Rodriguez Rocha, Catherine Faron-Zucker.

Partner : GAYAtech. This project was just accepted this year on the topic of semantic Web for e-learning. This is a joint project with Gayatech on the recommendation of pedagogical resources adapted to user profile and context in the EDUCLOUD 06 Serious Game. To get help in his quests and various quiz testing his knowledge, the gamer can use external digital resources (books, video, TV, Web) and an in-game social network to work with his teacher and comrades. In this context, and to meet the needs of GAYATECH developing edutainment solutions, the Semantic EDUCLOUD project aims to improve the recommendation of educational resources to learners in EDUCLOUD 06, by using semantic Web and social Web models and techniques.

Carnot Project Vigiglobe

Participants : Elena Cabrio, Serena Villata.

Partner : Vigiglobe.

This project was just accepted this year on the topic of Natural Language Argumentation on Twitter: Retrieval of Argumentative Structures and Reasoning. this is a joint project with Vigiglobe on the natural language processing of argumentation on Twitter to retrieve argumentative structures and reason on them. The goal of the project is to : (1) Automate the selection and annotation of tweets, i.e., retrieval of those tweets that can be considered as arguments (2) Automate the assignment of labels to the type of relation holding between arguments - positive relation or negative relation. (3) Create an argumentation graph illustrating the relations between the arguments about a certain subject, and the further application of argumentation semantics to compute the set of “winning” arguments This graph-based visualization provides a summary of the ongoing discussion on Twitter.

FUI PadDOC

Participants : Patrice Pena, Alain Giboin.

PadDOC goal is to contribute to accelerating the digital transition of citizen, local and regional authorities, administrations and enterprises, by : (1) developing an open standard and innovative software and hardware resources to facilitate nearby or distant administrative formalities and procedures; (2) improving the security of the holder’s personal data by putting these data under the exclusive control of the holder; (3) exploiting unmarked communicating supports (such as smartphones or tablets) for all chain actors. PadDOC partners are: Docapost BPO, Anyces, ABC SmartCard and the teams Rainbow, Media-Coding and Wimmics.Wimmics will contribute to: (1) the analysis, design and evaluation of the PadDOC security-oriented user interfaces; (2) the impact assessment of the chain of actors participating in the experiment to validate the viability of the PadDOC social system. The PadDOC project officially began in November 2014.

This year, Wimmics main contributions were: a state-of-the-art on user-centered privacy and security (leading to the identification of the security and privacy aspects to be taken into account, from a user’s point of view, in the design of a mobile device used to communicate personal data and documents); a field study of users performing administrative procedures from the point of view of security and privacy; and the functional mock-ups of the GUIs of the PadDOC mobile application to be used by the client of a commercial or administrative service.