Seminaire: Anna Korhonen (Universite de Cambridge) a l'Universite Paris 13

[Thierry Hamon]

Date: Thu, 24 May 2007 11:06:43 +0200
From: Thierry Poibeau <Thierry.Poibeau at lipn.univ-paris13.fr>
Message-Id: <40adea80643c6adb78c9fa5faaf1ddb5 at lipn.univ-paris13.fr>
X-url: http://www.cl.cam.ac.uk/~alk23/,
X-url: http://www-lipn.univ-paris13.fr/planfac/?lang=fr


Anna Korhonen (http://www.cl.cam.ac.uk/~alk23/, Université de
Cambridge, actuellement en visite au Laboratoire d'Informatique de
Paris-Nord) donnera un séminaire sur le développement de ressources
lexicales pour des applications de traitement automatique des langues
(résumé ci-dessous).

Le séminaire aura lieu le jeudi 31 mai à 15 heures, en salle B311 du 
LIPN (un plan d'accès est accessible ici : 
http://www-lipn.univ-paris13.fr/planfac/?lang=fr, le bâtiment B se 
situe au nord de l'université)


Résumé : Developing Lexical Resources for NLP Applications

In NLP, there is a pressing need to develop comprehensive and accurate
lexical resources for systems dealing with real-world applications
(e.g. high quality lexicons for information extraction and machine
translation). Such resources are critical for enhancing the
performance of systems and for improving their portability between
domains.  Currently, most lexical resources are developed manually by
linguists.  Manual work is costly, and the resulting resources require
extensive labour-intensive porting to new tasks. Automatic acquisition
of lexical information from repositories of text (e.g. text corpora,
the web) is a more promising and cost-effective approach to take. The
approach is now increasingly viable given recent advances in NLP and
machine learning technology, and significant progress has recently
been made in many areas of automatic lexical acquisition. In this
talk, I will describe the work we have conducted in Cambridge on
lexical acquisition, focusing on two areas: the extraction of
subcategorisation frames and lexical-semantic classes from corpora. I
will describe the techniques we employ in our work and discuss the
usefulness of the resulting information for practical application
tasks.


-------------------------------------------------------------------------
Message diffuse par la liste Langage Naturel <LN at cines.fr>
Informations, abonnement : http://www.atala.org/article.php3?id_article=48
English version       : 
Archives                 : http://listserv.linguistlist.org/archives/ln.html
                                http://liste.cines.fr/info/ln

La liste LN est parrainee par l'ATALA (Association pour le Traitement
Automatique des Langues)
Information et adhesion  : http://www.atala.org/
-------------------------------------------------------------------------