Section: New Results

Named Entity Recognition and Entity Linking

Participants : Rosa Stern, Benoît Sagot.

Identifying named entities is a widely studied issue in Natural Language Processing, because named entities are crucial targets in information extraction or retrieval tasks, but also for preparing further NLP tasks (e.g., parsing). Therefore a vast amount of work has been published that is dedicated to named entity recognition, i.e., the task of identification of named entity mentions (spans of text denoting a named entity), and sometimes types. However, real-life applications need not only identify named entity mentions, but also know which real entity they refer to; this issue is addressed in tasks such as knowledge base population with entity resolution and linking, which require an inventory of entities is required prior to those tasks in order to constitute a reference.

Cooperation of symbolic and statistical methods for named entity recognition and typing

Named entity recognition and typing is achieved both by symbolic and probabilistic systems. We have performed an experiment [62] for making the rule-based system NP, Sx Pipe's high-precision named entity recognition system developed at Alpage on AFP news corpora and which relies on the Aleda named entity database, interact with LIANE, a high-recall probabilistic system developed by Frédéric Béchet (LIF) and trained on oral transcriptions from the ESTER corpus. We have shown that a probabilistic system such as LIANE can be adapted to a new type of corpus in a non-supervised way thanks to large-scale corpora automatically annotated by NP. This adaptation does not require any additional manual annotation and illustrates the complementarity between numeric and symbolic techniques for tackling linguistic tasks.

Nomos, a statistical entity linking system

For information extraction from news wires, entities such as persons, locations or organizations are especially relevant in a knowledge acquisition context. Through a process of named entity recognition and entity linking applied jointly, we aim at the extraction and complete identification of these relevant entities, which are meant to enrich textual content in the form of metadata. In order to store and access extracted knowledge in a structured and coherent way, we aim at populating an ontological reference base with these metadata. We have pursued our efforts in this direction, using an approach where NLP tools have early access to Linked Data resources and thus have the ability to produce metadata integrated in the Linked Data framework. In particular, we have studied how the entity linking process in this task must deal with noisy data, as opposed to the general case where only correct entity identification is provided.

We use the symbolic named entity recognition system NP, a component of Sx Pipe, and use it as a mention detection module. Its output is then processed through our entity linking system, which is based on a supervised model learned from examples of linked entities. Since our named entity recognition is not deterministic, as opposed to other entity linking tasks where the gold named entity recognition results are provided, it is configured to remain ambiguous and non-deterministic, i.e., its output preserves a number of ambiguities which are usually resolved at this level. In particular, no disambiguation is made in the cases of multiple possible mentions boundaries (e.g., {Paris}+{Hilton} vs. {Paris Hilton}). In order to cope with possible false mention matches, which should be discarded as linking queries, the named entity recognition output is made more ambiguous by adding a not-an-entity alternative to each mention's candidate set for linking. The entity linking module's input therefore consists in multiple possible readings of sentences. For each reading, this module must perform entity linking on every possible entity mention by selecting their most probable matching entity. Competing readings are then ranked according to the score of entities (or sequence of entities) ranked first in each of them. The reading with no entity should also receive a score in order to be included in the ranking. The motivation for this joint task lies in the frequent necessity of accessing contextual and referential information in order to complete an accurate named entity recognition; thus the part where named entity recognition usually resolves a number of ambiguities is left for the entity linking module, which uses contextual and referential information about entities.

We have realized a first implementation of our system, as well as experiments and evaluation results. In particular, when using knowledge about entities to perform entity linking, we discuss the usefulness of domain specific knowledge and the problem of domain adaptation.

In 2012, improvements have been made to Nomos by combining the NP named entity detection module with LIANE, a probabilistic system developed by Frédéric Béchet (LIF) in order to better predict possible false matches. The linking step has also been enriched with the use of a more complete and autonomous knowledge base derived from Wikipedia, as well as new parameters and ranking functions for the prediction of the mention/entity alignment.

In the context of this linking task for the processing of AFP corpora and content enrichment with metadata, we conducted a deep study of Semantic Web recent developments and especially of the Linked Data initiatives in order to consider the integration of AFP metadata in these knowledge representation frameworks. On this topic as well as the enlarged view of entity linking for semantic annotation of textual content, discussions have taken place with Eric Charton (CRIM, Montréal, Canada) during 2012 Fall.

The Nomos system as well as the general process of content enrichment with metadata and reference base population has been presented at a dedicated workshop at NAACL in June 2012 (AKBC-WEKEX 2012).