We address a core aspect of the multilingual content synchronization task: the identification of novel, more informative or semantically equivalent pieces of information in two documents about the same topic. This can be seen as an application-oriented variant of textual entailment recognition where: i) T and H are in different languages, and ii) entail- ment relations between T and H have to be checked in both directions. Using a combination of lexical, syntactic, and semantic features to train a cross-lingual textual entailment system, we report promising results on different datasets.

Detecting Semantic Equivalence and Information Disparity in Cross-Lingual Documents

Mehdad, Yashar;Negri, Matteo;Federico, Marcello
2012

Abstract

We address a core aspect of the multilingual content synchronization task: the identification of novel, more informative or semantically equivalent pieces of information in two documents about the same topic. This can be seen as an application-oriented variant of textual entailment recognition where: i) T and H are in different languages, and ii) entail- ment relations between T and H have to be checked in both directions. Using a combination of lexical, syntactic, and semantic features to train a cross-lingual textual entailment system, we report promising results on different datasets.
978-1-937284-25-1
File in questo prodotto:
File Dimensione Formato  
acl2012-CS-SHORT.pdf

accesso aperto

Tipologia: Documento in Post-print
Licenza: DRM non definito
Dimensione 135.71 kB
Formato Adobe PDF
135.71 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/11582/85002
Citazioni
  • ???jsp.display-item.citation.pmc??? ND
social impact