A probabilistic lexical model for ranking textual inferences

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

Abstract

Identifying textual inferences, where the meaning of one text follows from another, is a general underlying task within many natural language applications. Commonly, it is approached either by generative syntactic-based methods or by "lightweight" heuristic lexical models. We suggest a model which is confined to simple lexical information, but is formulated as a principled generative probabilistic model. We focus our attention on the task of ranking textual inferences and show substantially improved results on a recently investigated question answering data set.

Original languageEnglish
Title of host publicationProceedings of the Main Conference and the Shared Task
PublisherAssociation for Computational Linguistics (ACL)
Pages237-245
Number of pages9
ISBN (Electronic)9781937284213
StatePublished - 2012
Event1st Joint Conference on Lexical and Computational Semantics, *SEM 2012 - Montreal, Canada
Duration: 7 Jun 20128 Jun 2012

Publication series

Name*SEM 2012 - 1st Joint Conference on Lexical and Computational Semantics
Volume1

Conference

Conference1st Joint Conference on Lexical and Computational Semantics, *SEM 2012
Country/TerritoryCanada
CityMontreal
Period7/06/128/06/12

All Science Journal Classification (ASJC) codes

  • Computational Theory and Mathematics
  • Theoretical Computer Science
  • Computer Science Applications

Cite this