Benoît Sagot's homepage  —  team ALMAnaCH (Inria / EPHE)

Research fellow in NLP (Natural Language Processing) at Inria, head of the ALMAnaCH joint laboratory (Inria Paris and EPHE)
Former engineer of the Corps des Télécommunications (X-ENST)

Research topics:

  • Development of lexical resources (morphological, syntactic, semantic), for French (syntactic lexicon Lefff, semantic lexicon WOLF) and other languages
  • Computational and quantitative morphology
  • Symbolic (LFG) and probabilistic (PCFG) parsing, POS tagging
  • Processing of raw corpora (named entity recognition and resolution, spelling correction, unsupervized segmentation…)
  • Formal Grammars (LCFRS, RCG)
  • Applications of NLP

Mail address :

Inria Paris (équipe ALMAnaCH)
2 rue Simone Iff
CS 42112
75589 Paris Cedex 12
Phone: +33 1 80 49 43 14

Activities :

  • Member of the Board of Inria Paris's Scientific Committee ("Comité des Projets") — 2016–
  • Member of the Scientific Council of the EquipEx Ortolang — 2013–
  • Member of the Restricted Scientific Council (RSC) of the LabEx (excellency cluster) EFL, former head of the research strand 6 Language Ressources — 2011–2015, now deputy head, and alternate member of the RSC
  • Member of the Executive Committee of the Corpus Écrits consortium, within theTGIR (very large research infrastructure) Huma-Num
  • Member of the International Relations Working Group of Inria's Scientific and Technological Orientation Council (COST-GTRI)
  • PI of the EDyLex project, funded by the ANR (French National Research Agency) — 2010–2013 (~800k€, 3 academic teams and 3 companies)
  • Member of the Board and former Secretary of ATALA
  • Evaluator for the ANR (French National Research Agency)
  • Organiser of WoLeR 2011, an ESSLLI 2011 Workshop on Lexical Resources
  • Guest editor with Núria Bel for a Special Issue of the TAL journal on Language Resources
  • Member of the program comitee or reviewer for Computational Linguistics, Language Resources and Evaluation, TAL journal, the student session of LACL 2005, the TALN 2007 workshop on high-level linguistic formalisms, and the TALN 2008, IIS 2008, ALTW 2008, TALN 2009, ACL 2009, TALN 2010, SPMRL 2010, TALN 2011, SPMRL 2011 conferences
  • Secondary reviewer for IJCNLP 2005, EACL 2006, TALN 2007 and LREC 2008
  • Member of the recruiting committee for various permanent research and/or teaching positions (3 in 2010, 3 in 2011, 1 in 2012, 1 in 2013, 2 in 2014)
  • Formerly (2007–2010), Secretary of redaction for the TAL journal


  • Co-supervisor of the PhD dissertation of Marion Baranes (industrial PhD at viavoo and Université Paris 7, between January 2012 and the PhD defense in October 2015)
  • Co-supervisor of the PhD dissertation of Valérie Hanoka ("CIFRE" PhD, Université Paris 7 — Verbatim Analysis, between January 2011 and the PhD defense in July 2015)
  • Co-supervisor of the PhD dissertation of Pierre Magistry (Allocataire Moniteur Université Paris 7, between September 2010 and the PhD defense in December 2013)
  • Co-supervisor of the PhD dissertation of Rosa Stern ("CIFRE" PhD, Université Paris 7 — Agence France-Presse, between September 2009 and the defense in June 2013)
  • Supervisor of Sarah Beniamine's Master 2 (Université Paris 7, 2014)
  • Examiner of the PhD dissertation of Rania Voskaki (Université Paris-Est Marne-la-Vallée, 2011)
  • Examiner of the PhD dissertation of Claire Mouton (Université Paris Sud, 2010)
  • Examiner of the PhD dissertation of Lionel Nicolas (Université de Nice, 2010)
  • Reviewer of the PhD dissertation of Juan Otero (University de Vigo, Spain, 2009)
  • Examiner of the PhD dissertation of Laurence Delort (University Paris 7, France, 2008)

Misc :

  • Translator (en->fr) of 3 chapters of the new edition of the Dragon Book (Aho, Lam, Sethi, Ullman)