home
about me papers résumé research links contact

current events


past events

  • Program Committee member: ACL 2007, 2009, 2011; CICLING 2008; CID 2011; COLING 2010; EMNLP 2009, 2010, 2011; IEEE-ICSC 2009; IJCNLP 2011; LSRL 2005; SuB 2008; TALN 2011; TLS 2008; ATALA 2010 Workshop on CRFs; ATALA 2010 Workshop on Corpus Annotation; NAACL/HLT 2009 Workshop on ILP for NLP; ...
  • Organizing Committee member: CID 2011; Tempeval-2: Evaluating Events, Time Expressions, and Temporal Relations; TLS 2004



research projects

Below is a list of some of the research projects that I am, or have been, involved with.

ongoing

  • STAC: Strategic Conversation, ERC Advance Grant, 2011-2016. PI: Nicholas Asher, CNRS Toulouse.
  • EDyLex: Dynamically Enriching Lexical resources in multilingual and multimodal applications. ANR, 2010-2012. PI: Benoît Sagot, INRIA Paris.

past

  • ITIPy: Automatic Itinerary Extraction from Travel Logs. INRIA-Aquitaine Region, 2010-2012. PI: Renaud Marlet, INRIA Bordeaux.
  • SEQUOIA: Large coverage probabilistic syntactic parsing of French. ANR, 2009-2011. PI: Alexis Nasr, University of Marseille.
  • SCRIBO: Semi-automatic and Collaborative Retrieval of Information Based on Ontologies, System@tic Paris-Region, 2008-2010. PI: Eric de la Clergerie, INRIA Paris.
  • AnnoDis: Discourse Annotation: tools and reference corpus for French, ANR, 2007-2009. PI: Nicholas Asher, CNRS Toulouse.
  • DiSCoR: Extracting and Using Discourse Structure to Resolve Anaphoric Dependencies: Combining Logico-Semantics and Statistical Approaches. NSF, 2006-2008. PIs: Nicholas Asher and Jason Baldridge, University of Texas at Austin.



students

current

  • Emmanuel Lassalle (PhD, 2010-), lexical induction and bridging resolution
  • Chloé Braud (PhD, 2011-), discourse parsing

past

  • André Bittar (PhD, 2011), now at XRCE, Grenoble
  • Chloé Braud (Master, 2011)
  • Emmanuel Lassalle (Master, 2010)
  • Altaf Rahman (Summer intern, 2011)
  • Alexis Vanacker (Summer intern, 2009)



open-source software and resources

I have contributed to a number of open source software and resources that are freely available to the NLP community.

  • CoRTex: Python suite implementing various state-of-the-art coreference resolution systems. LGPL.
  • FreDist: Distributional thesauri for French.
  • MElt: high-precision MEMM POS tagger for French. LGPL. Available from INRIA Forge
  • StatGram: state-of-the-art dependency parsers for French. LGPL.
  • TADM: High performance C++ and Python toolkit for training maximum entropy and perceptron models. LGPL.