Overview of Natural Language Processing at LIMSI, CNRS, France

--------------------------------------------------------------------
               ***Joint Seminar***

The Hong Kong University of Science & Technology
Department of Computer Science and Engineering
Department of Electronic and Computer Engineering
Human Language Technology Center
--------------------------------------------------------------------

Speaker:	Dr Pierre Zweigenbaum
		Senior Researcher at LIMSI (Computer Sciences Laboratory
		for Mechanics and Engineering Sciences)
		CNRS

Title:		"Overview of Natural Language Processing at LIMSI, CNRS,
		 France"

Date:		Wednesday, 29 July 2009

Time:		3:00pm-4:00pm

Venue:		Rm 2578, 2/F, (via lifts 29/30), HKUST

Abstract:

I shall present an overview of current projects in LIMSI's Natural Language
Processing team (ILES: "Written and Sign Language and Information"), which
span question-answering (French, English, and medical domain), information
extraction (including named entities, including in the medical domain),
corpora and classification, and the organisation of NLP challenges (question-
answering, French parsers, opinion mining). I shall also focus on current
work which takes advantage of (medical) monolingual comparable corpora to
find lay equivalents of specialized expressions (in English and French).


*************************
Biography:

Pierre Zweigenbaum graduated from École Polytechnique, Paris, France, in 1980,
from École Nationale Supérieure des Télécommunications (ENST) in 1982,
received an ENST PhD in Computer science in 1985, and the "Habilitation á
diriger des Recherches" in 1998 from Paris-North University.  He is currently 
Senior Researcher at LIMSI (Computer Sciences Laboratory for Mechanics and
Engineering Sciences), a unit of CNRS, the French National Center for
Scientific Research, and is Associate Professor at the National Institute of
Oriental Languages and Civilizations, where he teaches Natural Language
Engineering.  His research interests focus on Natural Language Processing
(NLP), from morphology to question answering, with a focus on specific
domains (medicine and medical terminology) and multilingual issues (alignment
in parallel and comparable corpora).