Complutense University Library

Textual entailment recognition based on dependency analysis and WordNet

Herrera de la Cruz, Jesús and Peñas, Anselmo and Verdejo, Felisa (2006) Textual entailment recognition based on dependency analysis and WordNet. In MLCW 2005. Lecture Notes in Artificial Intelligence, 3944 . Springer-Verlag, Berlin, pp. 231-239. ISBN 3 540 33427 0 (In Press)

[img]
Preview
PDF
234kB
View download statistics for this eprint

==>>> Export to other formats

Abstract

The Recognizing Textual Entailment System shown here is based on the use of a broad-coverage parser to extract dependency relationships; in addition, WordNet relations are used to recognize entailment at the lexical level. The work investigates whether the mapping of dependency trees from text and hypothesis give better evidence of entailment than the matching of plain text alone. While the use of WordNet seems to improve system's performance, the notion of mapping between trees here explored (inclusion) shows no improvement, suggesting that other notions of tree mappings should be explored such as tree edit distances or tree alignment distances.

Item Type:Book Section
Uncontrolled Keywords:Reconocimiento de implicación textual; Análisis de dependencias; Recognising textual entailment; Dependency analysis
Subjects:Sciences > Computer science > Artificial intelligence
Humanities > Philology > Linguistics
ID Code:5526
Deposited On:04 Apr 2006
Last Modified:06 Feb 2014 07:44

Repository Staff Only: item control page