Seminaire: Kevin Cohen, Software testing and quality assurance for NLP, LIMSI, 16 Juin 2014

[Thierry Hamon]

Date: Mon, 26 May 2014 15:49:19 +0200
From: Aurélie Névéol <aneveol at gmail.com>
Message-ID: <CAPBFUoVr20egZJpA9d662vHF8wNdWzL9Vyzz93_2OzCFUFYceA at mail.gmail.com>


Bonjour,

Le LIMSI-CNRS recevra Kevin B. Cohen de l’Université du Colorado *lundi
16 Juin à 14h*. Il présentera à cette occasion un exposé intitulé: In
the context of natural language processing, doing "software testing" is
otherwise known as doing linguistics. Un descriptif plus détaillé de
l’exposé et du parcours de l’orateur se trouvent à la fin de ce
courriel.

Le séminaire, ouvert à tous, aura lieu à Orsay, dans la salle de
conférence du bâtiment 508 sur la « plateau » du Campus de l’Université
Paris Sud. Des informations détaillées sur l’accès au laboratoire sont
disponibles sur le site du LIMSI http://www.limsi.fr/Pratique/acces/.

Cordialement,

Aurélie

------------------------------------------------------------------------


*Title*: In the context of natural language processing, doing "software
testing" is otherwise known as doing linguistics

*Abstract*: Software testing and quality assurance for natural language
processing has rarely been studied, despite the fact that natural
language processing applications present unique challenges for these
tasks.  Despite this lack of study, a fully-developed methodology is
available, known as field methods and coming from the field of
descriptive linguistics.  In this talk, I will present an application of
field methods to software testing in the biomedical text mining domain
and show how it can yield fine-grained insight into what an application
is good at and what it is bad at.

*Short bio*: Kevin Bretonnel Cohen leads the Biomedical Text Mining
Group in the Computational Bioscience Program at the University of
Colorado School of Medicine.  He is the chair of the Association for
Computational Linguistics special interest group on biomedical natural
language processing.  His research interests include computational
lexical semantics, ontologies, named entity recognition and
normalization, information extraction, corpus linguistics, information
retrieval, question answering, and software testing and quality
assurance for natural language processing applications.

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

ATALA décline toute responsabilité concernant le contenu des
messages diffusés sur la liste LN
-------------------------------------------------------------------------