Information Extraction

Information Extraction, Focused Information Retrievel, and Question-Answering

The methods developed in this topic complement mainstream information retrieval techniques, whose main goal is document retrieval, by putting more emphasis on a precise analysis of text contents. Their are targeted for:

  • Information extraction: spotting targeted information in texts, with entity and relation extraction
  • Focused information retrieval: locating target information in documents to answer a query, and more
    specifically question-answering


  • Named-Entity recognition in general and specialized domain: recognition of complex NE types, dealing with lexical sparsity
  • Relation extraction in general and specialized domain, with supervised and unsupervised approaches, based on surface and structured representations
  • Event recognition and temporal information, thematic timelines
  • Opinion mining: building of a lexicon
  • Semantic inference and reasoning for answering question by searching a text or a knowledge base

Campus universitaire bât 507
Rue du Belvédère
F - 91405 Orsay cedex
Tél +33 (0) 1 69 15 80 15


LIMSI in numbers

8 Research Teams
100 Researchers
40 Technicians and Engineers
60 Doctoral Students
70 Trainees

 Paris-Sud University new window


Paris-Saclay University new window