top of page

Strand 5 : Computational Semantic Analysis

Updated: Jun 28, 2021

Manager : Thierry Charnois, LIPN Paris 13; co-responsable : Benoît Crabbé LLF Université de Paris

In the field of computational linguistics, Strand 5 focuses on semantic analysis and its application in various content access tools (e.g. information extraction, indexing, summarization), which may be based on different semantic representations. Models, methods and computations and - in some cases - tools have been proposed to describe and model different semantic phenomena, but these phenomena have generally been considered in isolation and with heterogeneous computation models. The challenge is to evaluate these different semantic models, to operationalize and integrate them to produce rich, overlaying and consistent semantic analyses, in the same way that robust and good quality syntax parsers have been produced.

The objective is to intensify research on the integration of semantic models and methods through the collaboration of different computational linguistics teams (Alpage, Lattice, LIPN, LPP-P3) and the confrontation of their heterogeneous results on syntactic analysis, textual analysis, corpus analysis and processing, text-based inferential reasoning, knowledge acquisition from texts, machine learning and tools for accessing textual content.

Strand 5 focuses on the analysis of French but particular attention is paid to the identification of language-independent methods that allow the analysis of a wide range of languages for which resources are available. This is indeed a promising approach for equipping poorly equipped languages used in Strands 2 and 3.

The axis focuses on written and oral language. The needs for analysis of spoken language are increasing and one of the challenges is to integrate in the semantic analysis of oral features such as dysfluencies to compensate for the low quality of the results obtained on oral transcriptions.

The Strand has 6 sub-axes :

- Historical and reflexive perspective (HP)

- Constitution and annotation of corpora for semantic analysis (AI)

- Semi-supervised learning for deep syntax analysis (SSL)

- Specific semantic analysis and processing (SSP)

- Knowledge Acquisition Methods (KA)

- Applications: towards an enriched access to text content (APP)

Actual Strand 5 operations (2020-2024)

SSL5 Shallow semantic analysis Marie Candito (LLF) – Joseph Leroux (LIPN)

SSL6 Semi-supervised Semantic Analysis Joseph Leroux (LIPN)

SSL7 MetaSem: Towards more semantic metagrammars Djamé Seddah – Eric de la Clergerie

SPP6 Word sense disambiguation and sense induction Lucie Barque – Marie Candito (LLF)

SPP7 Computational and Cognitive modeling of the processing of syntactic and semantic information Benoît Crabbé (LLF)

KA2/APP2 Extraction of semantic relations and applications Haïfa Zargayouna (LIPN)

APP4 RENFO: Expert research on the web through semantic extraction of bio-professional traces from the web Jorge Garcia Flores (LIPN)

APP5 When Aliens meet Predators : Building Context-Enhanced NLP Tools Djamé Seddah

APP6 Geo-NN: Geolocalisation in Social Media using Deep Neural Networks Davide Buscaldi (LIPN)

APP7 Legal rule analysis Adeline Nazarenko (LIPN)

HRP2 Graph-based semantic analysis Adeline Nazarenko (LIPN)

KA5 Cross-lingual and multilingual alignment of semantic Resources Haïfa Zargayouna (LIPN)

Listes des opérations de recherche précédentes (2015-2020)

Perspective historique et réflexive (HP)

Constitution et annotation de corpus pour l’analyse sémantique (IA)

Apprentissage semi-supervisé pour l’analyse syntaxique profonde (SSL)

Analyses et traitements sémantiques spécifiques (SSP)

Méthodes d’acquisition de connaissances (KA)

Conception et développement de nouvelles méthodes d’accès au contenu textuel (APP)


Post: Blog2_Post
bottom of page