Syntactic/semantic structures for textual entailment recognition

Yashar Mehdad, Alessandro Moschitti, Fabio Massimo Zanzotto

Research output: Chapter in Book/Report/Conference proceedingConference contribution

20 Citations (Scopus)

Abstract

In this paper, we describe an approach based on off-the-shelf parsers and semantic resources for the Recognizing Textual Entailment (RTE) challenge that can be generally applied to any domain. Syntax is exploited by means of tree kernels whereas lexical semantics is derived from heterogeneous resources, e.g. WordNet or distributional semantics through Wikipedia. The joint syntactic/semantic model is realized by means of tree kernels, which can exploit lexical relatedness to match syntactically similar structures, i.e. whose lexical compounds are related. The comparative experiments across different RTE challenges and traditional systems show that our approach consistently and meaningfully achieves high accuracy, without requiring any adaptation or tuning.

Original languageEnglish
Title of host publicationNAACL HLT 2010 - Human Language Technologies: The 2010 Annual Conference of the North American Chapter of the Association for Computational Linguistics, Proceedings of the Main Conference
Pages1020-1028
Number of pages9
Publication statusPublished - 1 Dec 2010
Externally publishedYes
Event2010 Human Language Technologies Conference ofthe North American Chapter of the Association for Computational Linguistics, NAACL HLT 2010 - Los Angeles, CA, United States
Duration: 2 Jun 20104 Jun 2010

Other

Other2010 Human Language Technologies Conference ofthe North American Chapter of the Association for Computational Linguistics, NAACL HLT 2010
CountryUnited States
CityLos Angeles, CA
Period2/6/104/6/10

Fingerprint

semantics
Wikipedia
resources
syntax
Entailment
Semantic Structure
Syntax
experiment
Resources
Kernel
Parsers
Experiment
Tuning
Lexical Semantics
WordNet

ASJC Scopus subject areas

  • Language and Linguistics
  • Linguistics and Language

Cite this

Mehdad, Y., Moschitti, A., & Zanzotto, F. M. (2010). Syntactic/semantic structures for textual entailment recognition. In NAACL HLT 2010 - Human Language Technologies: The 2010 Annual Conference of the North American Chapter of the Association for Computational Linguistics, Proceedings of the Main Conference (pp. 1020-1028)

Syntactic/semantic structures for textual entailment recognition. / Mehdad, Yashar; Moschitti, Alessandro; Zanzotto, Fabio Massimo.

NAACL HLT 2010 - Human Language Technologies: The 2010 Annual Conference of the North American Chapter of the Association for Computational Linguistics, Proceedings of the Main Conference. 2010. p. 1020-1028.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Mehdad, Y, Moschitti, A & Zanzotto, FM 2010, Syntactic/semantic structures for textual entailment recognition. in NAACL HLT 2010 - Human Language Technologies: The 2010 Annual Conference of the North American Chapter of the Association for Computational Linguistics, Proceedings of the Main Conference. pp. 1020-1028, 2010 Human Language Technologies Conference ofthe North American Chapter of the Association for Computational Linguistics, NAACL HLT 2010, Los Angeles, CA, United States, 2/6/10.
Mehdad Y, Moschitti A, Zanzotto FM. Syntactic/semantic structures for textual entailment recognition. In NAACL HLT 2010 - Human Language Technologies: The 2010 Annual Conference of the North American Chapter of the Association for Computational Linguistics, Proceedings of the Main Conference. 2010. p. 1020-1028
Mehdad, Yashar ; Moschitti, Alessandro ; Zanzotto, Fabio Massimo. / Syntactic/semantic structures for textual entailment recognition. NAACL HLT 2010 - Human Language Technologies: The 2010 Annual Conference of the North American Chapter of the Association for Computational Linguistics, Proceedings of the Main Conference. 2010. pp. 1020-1028
@inproceedings{f22edf4777204fcaa0a361869d3ebab2,
title = "Syntactic/semantic structures for textual entailment recognition",
abstract = "In this paper, we describe an approach based on off-the-shelf parsers and semantic resources for the Recognizing Textual Entailment (RTE) challenge that can be generally applied to any domain. Syntax is exploited by means of tree kernels whereas lexical semantics is derived from heterogeneous resources, e.g. WordNet or distributional semantics through Wikipedia. The joint syntactic/semantic model is realized by means of tree kernels, which can exploit lexical relatedness to match syntactically similar structures, i.e. whose lexical compounds are related. The comparative experiments across different RTE challenges and traditional systems show that our approach consistently and meaningfully achieves high accuracy, without requiring any adaptation or tuning.",
author = "Yashar Mehdad and Alessandro Moschitti and Zanzotto, {Fabio Massimo}",
year = "2010",
month = "12",
day = "1",
language = "English",
isbn = "1932432655",
pages = "1020--1028",
booktitle = "NAACL HLT 2010 - Human Language Technologies: The 2010 Annual Conference of the North American Chapter of the Association for Computational Linguistics, Proceedings of the Main Conference",

}

TY - GEN

T1 - Syntactic/semantic structures for textual entailment recognition

AU - Mehdad, Yashar

AU - Moschitti, Alessandro

AU - Zanzotto, Fabio Massimo

PY - 2010/12/1

Y1 - 2010/12/1

N2 - In this paper, we describe an approach based on off-the-shelf parsers and semantic resources for the Recognizing Textual Entailment (RTE) challenge that can be generally applied to any domain. Syntax is exploited by means of tree kernels whereas lexical semantics is derived from heterogeneous resources, e.g. WordNet or distributional semantics through Wikipedia. The joint syntactic/semantic model is realized by means of tree kernels, which can exploit lexical relatedness to match syntactically similar structures, i.e. whose lexical compounds are related. The comparative experiments across different RTE challenges and traditional systems show that our approach consistently and meaningfully achieves high accuracy, without requiring any adaptation or tuning.

AB - In this paper, we describe an approach based on off-the-shelf parsers and semantic resources for the Recognizing Textual Entailment (RTE) challenge that can be generally applied to any domain. Syntax is exploited by means of tree kernels whereas lexical semantics is derived from heterogeneous resources, e.g. WordNet or distributional semantics through Wikipedia. The joint syntactic/semantic model is realized by means of tree kernels, which can exploit lexical relatedness to match syntactically similar structures, i.e. whose lexical compounds are related. The comparative experiments across different RTE challenges and traditional systems show that our approach consistently and meaningfully achieves high accuracy, without requiring any adaptation or tuning.

UR - http://www.scopus.com/inward/record.url?scp=79959204960&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=79959204960&partnerID=8YFLogxK

M3 - Conference contribution

SN - 1932432655

SN - 9781932432657

SP - 1020

EP - 1028

BT - NAACL HLT 2010 - Human Language Technologies: The 2010 Annual Conference of the North American Chapter of the Association for Computational Linguistics, Proceedings of the Main Conference

ER -