Anselmo Peñas: "Paraphrasis of Noun Compounds"

Ponente: A. Peñas (NLP&IR-UNED)

Fecha: lunes 7 de mayo de 2012, a las 12h00

Lugar de celebración: Sala 1.26, Facultad de Psicología, UNED (mapa)

 

Abstract

A predicate is usually omitted from text when it is highly predictable from the context. This omission is due to the effort optimization that humans perform during the language generation process. Authors omit the information that they know the addressee is able to recover effortlessly. Most noun-noun structures including genitives and compounds are result of this process. The goal of this work is to generate automatically and without supervision the paraphrases that make explicit the omitted predicate in these noun-noun structures. The method is general enough to address also the cases were components are Named Entities. The resulting paraphrasing axioms are necessary for recovering the semantics of a text, and therefore, useful for applications such as Question Answering.

 

Bio

Anselmo Peñas is Associate Professor in the School of Computing, Distance Learning University of Spain, where he is researcher in the UNED NLP & IR Group since 1998. He obtained the PhD degree with special distinction and award in 2002 and also holds the Award of the Spanish Society for the Natural Language Processing. He has participated in several European projects such as EuroWordNet, CLEF and TrebleCLEF projects, News Engine Web Services project (NEWS), or the European Schools Treasury Browser project (ETB). A. Peñas has a book on Linguistic Techniques applied to Information Retrieval and more than 60 research papers on this topic, with special interest in multilingualism, interactivity and evaluation. Currently, he coordinates the Question Answering Track at CLEF.

 

Lugar de Celebración

Sala 1.26 (Sala de Juntas, primera planta)
Facultad Psicología, UNED
c/ Juan del Rosal, 10
Ciudad Universitaria
28040 Madrid

Materiales

Próximamente...

 

 
RocketTheme Joomla Templates