A machine learning approach to textual entailment recognition

Fabio Massimo Zanzotto, Marco Pennacchiotti, Alessandro Moschitti

Research output: Contribution to journalArticle

48 Citations (Scopus)

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.

Original languageEnglish
Pages (from-to)551-582
Number of pages32
JournalNatural Language Engineering
Volume15
Issue number4
DOIs
Publication statusPublished - 1 Oct 2009
Externally publishedYes

Fingerprint

Learning systems
Semantics
semantics
Syntactics
Learning algorithms
learning
experiment
interaction
Experiments
Entailment
Machine Learning
Expressive
Modeling
Semantic Features
Experiment
Semantic Relations
Interaction
Syntax

ASJC Scopus subject areas

  • Software
  • Artificial Intelligence

Cite this

A machine learning approach to textual entailment recognition. / Zanzotto, Fabio Massimo; Pennacchiotti, Marco; Moschitti, Alessandro.

In: Natural Language Engineering, Vol. 15, No. 4, 01.10.2009, p. 551-582.

Research output: Contribution to journalArticle

Zanzotto, Fabio Massimo ; Pennacchiotti, Marco ; Moschitti, Alessandro. / A machine learning approach to textual entailment recognition. In: Natural Language Engineering. 2009 ; Vol. 15, No. 4. pp. 551-582.
@article{b327e46ba58540a2a60142a383f04430,
title = "A machine learning approach to textual entailment recognition",
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.",
author = "Zanzotto, {Fabio Massimo} and Marco Pennacchiotti and Alessandro Moschitti",
year = "2009",
month = "10",
day = "1",
doi = "10.1017/S1351324909990143",
language = "English",
volume = "15",
pages = "551--582",
journal = "Natural Language Engineering",
issn = "1351-3249",
publisher = "Cambridge University Press",
number = "4",

}

TY - JOUR

T1 - A machine learning approach to textual entailment recognition

AU - Zanzotto, Fabio Massimo

AU - Pennacchiotti, Marco

AU - Moschitti, Alessandro

PY - 2009/10/1

Y1 - 2009/10/1

N2 - 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.

AB - 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.

UR - http://www.scopus.com/inward/record.url?scp=76449118321&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=76449118321&partnerID=8YFLogxK

U2 - 10.1017/S1351324909990143

DO - 10.1017/S1351324909990143

M3 - Article

AN - SCOPUS:76449118321

VL - 15

SP - 551

EP - 582

JO - Natural Language Engineering

JF - Natural Language Engineering

SN - 1351-3249

IS - 4

ER -