Publicado em: 26/03/2015

Prof. Eric Wehrli (University of Geneva) palestra no INF

No dia 31 de março, o Prof. Eric Wehrli, da University of Geneva, ministrará a palestra “Collocations and Anaphora Resolution in Machine Translation”, que acontecerá as 10h30min, no Auditório Prof. Castilho (prédio 43424), do Instituto de Informática. O Prof. Eric estará visitando o INF,  entre os dias 25 de março e 10 de abril, pelo projeto europeu PARSEME.

Título: Collocations and Anaphora Resolution in Machine Translation

Palestrante: Prof. Eric Wehrli
LATL-CUI
University of Geneva

Data: 31/03/2015
Horário: 10.30
Local: Instituto de Informática, Universidade Federal do Rio Grande do Sul
Prédio 43424(72) – sala Auditório Prof. Castilho

Abstract:
Collocation identification and anaphora resolution are widely recognized as major issues for natural language processing, and particularly for machine translation. An abundant literature has been dedicated to each of those issues, but to the best of our knowledge their intersection domain – collocations in which the base term has been pronominalized – has hardly been treated.
In this talk, I will present our (modest) contribution towards filling this gap, focusing on the translation from English to French of collocations of the type verb-direct object (to break a record, to make an appointment, to make a case, to take a break, etc.), with and without pronominalization of the complement.

————–

Eric Wehrli
– Studies in theoretical linguistics (PhD, McGill University, 1979)
and computer science (MS, University of Neuchâtel, 2001)
– Assistant professor at the Linguistics Department of the University
of California (UCLA) – Professor of linguistics and computer science
at the University of Geneva since 1988.
– Dean of the Faculty of Humanities, Univ. of Geneva 2005-2011
– Director of the Centre universitaire d’informatique (CUI), Univ. of
Geneva since 2013

Main interests: natural language processing (parsing, terminology
extraction, translation), theoretical syntax

Selected publications

– L’analyse syntaxique des langues naturelles : problèmes et méthodes,
Paris, Masson, 1997.
– (with Violeta Seretan) “Syntactic concordancing and multi-word
expression detection”, International Journal of Data Mining, Modelling
and Management, 5.2. pp. 158-181, 2013.
– (with Luka Nerima) “The Fips Multilingual Parser”, in N. Gala, R.
Rapp (eds.), Language Production, Cognition and the Lexicon, Text,
Speech and Language Technology 48, Springer Verlag, pp. 473-490, 2015.