Towards a Probabilistic Model for Lexical Entailment

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

Abstract

While modeling entailment at the lexical-level is a prominent task, addressed by most textual entailment systems, it has been approached mostly by heuristic methods, neglecting some of its important aspects. We present a probabilistic approach for this task which covers aspects such as differentiating various resources by their reliability levels, considering the length of the entailed sentence, the number of its covered terms and the existence of multiple evidence for the entailment of a term. The impact of our model components is validated by evaluations, which also show that its performance is in line with the best published entailment systems.

Original languageEnglish
Title of host publicationTextInfer 2011 - Workshop on Textual Entailment at the Conference on Empirical Methods in Natural Language Processing, EMNLP 2011 - Proceedings
EditorsSebastian Pado, Stefan Thater
PublisherAssociation for Computational Linguistics (ACL)
Pages10-19
Number of pages10
ISBN (Electronic)1937284158, 9781937284152
StatePublished - 2011
Event2011 Workshop on Textual Entailment, TextInfer 2011 at the Conference on Empirical Methods in Natural Language Processing, EMNLP 2011 - Edinburgh, United Kingdom
Duration: 30 Jul 2011 → …

Publication series

NameTextInfer 2011 - Workshop on Textual Entailment at the Conference on Empirical Methods in Natural Language Processing, EMNLP 2011 - Proceedings

Conference

Conference2011 Workshop on Textual Entailment, TextInfer 2011 at the Conference on Empirical Methods in Natural Language Processing, EMNLP 2011
Country/TerritoryUnited Kingdom
CityEdinburgh
Period30/07/11 → …

All Science Journal Classification (ASJC) codes

  • Computer Science Applications
  • Computational Theory and Mathematics
  • Information Systems

Fingerprint

Dive into the research topics of 'Towards a Probabilistic Model for Lexical Entailment'. Together they form a unique fingerprint.

Cite this