Seminaire: Alpage, Kenji Sagae, lundi 12 octobre 2009

[Thierry Hamon]

Date: Fri, 09 Oct 2009 16:13:38 +0200
From: bcrabbe at linguist.jussieu.fr
Message-ID: <1255097618.4acf4512db215 at kmail.linguist.univ-paris-diderot.fr>


******************* Séminaire Alpage *******************

         Séminaire de l'école doctorale de Paris 7

Il s'agit du séminaire de recherche en linguistique informatique
organisé par l'équipe Alpage, Alpage est une équipe mixte Inria --
Paris 7 qui centre ses intérêts scientifiques autour de l'analyse
syntaxique automatique et du traitement du discours pour la langue
française.

Le séminaire se tient le lundi de 14.30 à 16.00 tous les 15 jours.  
Il aura lieu en salle des thèses de l'UFR GHSS (université Paris 7),
105 rue de Tolbiac, Dalles "LES OLYMPIADES" Il y a un franprix le
bâtiment « tour Montréal » est juste sur la gauche *Adressez vous aux
appariteurs pour l'indication des salles.

Toute personne intéressée est la bienvenue.

***********************************************************

Lundi 12 octobre 2009, Kenji Sagae (University of Southern California) nous
parlera de :

Practical analysis of natural language syntax, semantics and discourse
with shift-reduce algorithms

Résumé :

Automatic analysis of the structure of natural language through
syntactic parsing techniques has long been considered of great
potential value in the study of language, the development of
language-enabled systems and interfaces, and the application of
language technologies (such as machine translation, question answering
and text mining) to the rapidly growing body of information in the
form of machine readable text. However, for many years parsing systems
suffered from lack of robustness and efficiency to deal with
large-scale tasks.  Recent research on linear-time parsers that learn
from annotated data has opened new possibilities for how these and
other issues in practical parsing technologies can be addressed.

In this talk I will first present a simple and effective parsing
framework that addresses the main challenges in the deployment of
parsing technologies in practical tasks. I will show how the
combination of machine learning and a parsing approach inspired by
Knuth's deterministic LR algorithm produces parsers that are fast,
robust and accurate. I will then discuss the application of this
parsing framework in areas as diverse as child language analysis,
bioinformatics, and virtual human dialogue systems, and its extension
to perform analysis of semantic roles and discourse structure.

Bio:

Kenji Sagae is a research scientist in the Institute for Creative
Technologies at the University of Southern California, where he works
on natural language processing for virtual humans and related systems.
 Before joining USC in June of 2008, he was a research associate in
the Computer Science department of the University of Tokyo, where he
worked on natural language processing for bioinformatics and
information extraction.  He received a PhD in Language Technologies
from the School of Computer Science at Carnegie Mellon University in
2006. His dissertation research focused on automatic syntactic
analysis of transcripts of dialogues between children and adult
caregivers. He is currently the Information Officer for SIGPARSE, and
his parsing software is used by several research groups in child
language and information extraction for biomedical text.

Séminaires à venir :

9/11   : R. Basili(Roma)
16/11 : G. Lapalme (Montreal)
23/11 : L. Barque (Lille)
30/11 : P. Merlo (Genève)


-------------------------------------------------------------------------
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/
-------------------------------------------------------------------------