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.

Zanzotto, F.m., Pennacchiotti, M., Moschitti, A. (2009). A Machine learning approach to textual entailment recognition. NATURAL LANGUAGE ENGINEERING, 15 - http://www.scimagojr.com/journalsearch.php?q=28380&tip=sid&clean=0(4), 551-582 [10.1017/S1351324909990143].

A Machine learning approach to textual entailment recognition

ZANZOTTO, FABIO MASSIMO;MOSCHITTI, ALESSANDRO
2009-01-01

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.
2009
Pubblicato
Rilevanza internazionale
Articolo
Esperti anonimi
Settore ING-INF/05 - SISTEMI DI ELABORAZIONE DELLE INFORMAZIONI
English
natural language processing; machine learning; textual entailment recognition
Zanzotto, F.m., Pennacchiotti, M., Moschitti, A. (2009). A Machine learning approach to textual entailment recognition. NATURAL LANGUAGE ENGINEERING, 15 - http://www.scimagojr.com/journalsearch.php?q=28380&tip=sid&clean=0(4), 551-582 [10.1017/S1351324909990143].
Zanzotto, Fm; Pennacchiotti, M; Moschitti, A
Articolo su rivista
File in questo prodotto:
File Dimensione Formato  
2009_JNLE_ZanzottoPennacchiottiMoschitti.pdf

accesso aperto

Descrizione: Articolo Principale
Licenza: Copyright dell'editore
Dimensione 303.41 kB
Formato Adobe PDF
303.41 kB Adobe PDF Visualizza/Apri

I documenti in IRIS sono protetti da copyright e tutti i diritti sono riservati, salvo diversa indicazione.

Utilizza questo identificativo per citare o creare un link a questo documento: https://hdl.handle.net/2108/40790
Citazioni
  • ???jsp.display-item.citation.pmc??? ND
  • Scopus 62
  • ???jsp.display-item.citation.isi??? 28
social impact