Research projects (ERTIM)

- CNES (2019-2020): The aim of this study is to develop an approach for detecting causal structures (markers and their arguments) in technical text based both on syntactic analyses of this type of text and on observable semantic relations that manifest the existence of causal relations. This study will focus on a selection of patents in the field of space engineering.

- TALAD (2017-2021): Automatic discourse analysis and processing

- MultiTAL (2015-2016) : Documentation and expertise platform for tools and resources for the automatic processing of Oriental and poorly endowed languages

- GAELL (2014-2015): Production and online release of an automatic generator of Estonian exercises, taken from CoPEF, a Franco-Estonian Parallel Corpus of around 65 million words (see also AideMoi, an L2 reading aid)

- INaLCO MANTAL (2014-2017): morpho-syntactic analysis of Bambara using a partially disambiguated corpus and machine learning techniques (languages covered: Bambara)

- SPC Blanc APRECIADO (2013-2016): Analyse et spatialisation des Perceptions et Représentations sociales des Changements environnementaux en Afrique De l'Ouest sahélo-soudanienne (Paris Nord, Paris Diderot, Inalco) (languages covered: French, English, Peul, Wolof, Djerma)

- ANR Contint ACCORDYS (2012-2016): Agrégation de Contenus et de COnaissances pour Raisonner à partir de cas de DYSmorphologie foetale (INSERM, LIMSI, Inalco, Hôpital Trousseau, ANTIDOT) (languages processed: French, English)

- ANR MDCo C-Mantic (2007-2010): Methodology and tools for the application of corpus semantics to the filtering of documentary masses (INALCO, LINA, LIMSI, INSERM) (languages covered: French, English, Chinese)

- ANR TECSAN VIGITERMES (2007-2009): Towards better signal detection and knowledge management in pharmacovigilance (INSERM, IM&Bio, INALCO, Rennes 1, LORIA, DSPIM, Mondeca, Temis, etc.) (languages covered: French, English, Japanese)

- Socrates-Lingua ALPCU (2005-2007): Learning the National Languages of Central and Eastern European Countries applying to join the European Union (Inalco, Sofia, Maribor, Banská Bistrica) (languages covered: Bulgarian, Slovak, Slovenian)

- MENR PrAX (2005-2006): Prévenir le Racisme et la Xénophobie sur Internet: ressources pédagogiques pour l'analyse critique de documents racistes et xénophobes sur l'Internet (Inalco, ATILF) (languages handled: French)

- PUF e-lexiques (2004-2006): Lexiques trilingues médias, relations internationales, langue des affaires (languages handled: French English Arabic)

- CNRS PI-TCAN DECO (2005):Discovery and exploitation of comparable corpora for information access (LINA, I, Tokyo, Xerox) (languages handled: French, English, Japanese)

- CNRS PI-TCAN PertoMed (2005): Production and evaluation of terminological and ontological resources in the field of medicine (INSERM, ERSS, Inalco)

- Safer Internet PRINCIP (2002-2004): Platform for the Research, Identification and Neutralization of Illegal and Harmful Content on the Internet (LIP6, Inalco, Dublin, Magdeburg) (languages handled: French, English, German)

- Technolangue Evalda (2002-2005): Concerted Research Action on Document Alignment and its Evaluation (ELDA, LIA, LIDILEM, LIST, LORIA, Xerox, etc.) (languages handled: French, English, German).) (languages covered: French, English, Arabic, etc.)

- SAFIR (2002-2003): Système multi-Agent de Filtrage d'Information sur les Réseaux (LIP6, Inalco, Xerox, EDF, DIP System) (languages handled: French, English, German)

- Socrates Lingua (1997-1998) ATHOS: tool for raising awareness of multilingual comprehension: discovery and contributions of modern Greek in European languages (languages covered: Greek)

- MedMed (1993-1996) Médiation Médicale: Tools to help learn medical Bambara for use by the Institut d'Ophtalmologie Tropicale de l'Afrique (language covered: Bambara)