A confidence model for syntactically-motivated entailment proofs

Asher Stern, Ido Dagan

Research output: Contribution to journalConference articlepeer-review

29 Scopus citations

Abstract

This paper presents a novel method for recognizing textual entailment which derives the hypothesis from the text through a sequence of parse tree transformations. Unlike related approaches based on tree-edit-distance, we employ transformations which better capture linguistic structures of entailment. This is achieved by (a) extending an earlier deterministic knowledge-based algorithm with syntactically-motivated on-the-fly transformations, and (b) by introducing an algorithm that uniformly learns costs for all types of transformations. Our evaluations and analysis support the validity of this approach.

Original languageEnglish
Pages (from-to)455-462
Number of pages8
JournalInternational Conference Recent Advances in Natural Language Processing, RANLP
StatePublished - 2011
Event8th International Conference on Recent Advances in Natural Language Processing, RANLP 2011 - Hissar, Bulgaria
Duration: 12 Sep 201114 Sep 2011

Fingerprint

Dive into the research topics of 'A confidence model for syntactically-motivated entailment proofs'. Together they form a unique fingerprint.

Cite this