A machine learning approach to textual entailment recognition
- 16 September 2009
- journal article
- research article
- Published by Cambridge University Press (CUP) in Natural Language Engineering
- Vol. 15 (4) , 551-582
Abstract
Designing models for learning textual entailment recognizers from annotated examples is not an easy task, as it requires modeling the semantic relations and interactions involved between two pairs of text fragments. In this paper, we approach the problem by first introducing the class of pair feature spaces, which allow supervised machine learning algorithms to derive first-order rewrite rules from annotated examples. In particular, we propose syntactic and shallow semantic feature spaces, and compare them to standard ones. Extensive experiments demonstrate that our proposed spaces learn first-order derivations, while standard ones are not expressive enough to do so.Keywords
This publication has 6 references indexed in Scilit:
- What Syntax Can Contribute in the Entailment TaskLecture Notes in Computer Science, 2006
- Feature space interpretation of SVMs with indefinite kernelsIEEE Transactions on Pattern Analysis and Machine Intelligence, 2005
- Automatic Labeling of Semantic RolesComputational Linguistics, 2002
- Applied morphological processing of EnglishNatural Language Engineering, 2001
- WordNetCommunications of the ACM, 1995
- The Logic of Typed Feature Structures1992