ECNUCS: Recognizing cross-lingual textual entailment using multiple text similarity and text difference measures

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

3 Scopus citations

Abstract

This paper presents our approach used for cross-lingual textual entailment task (task 8) organized within SemEval 2013. Cross-lingual textual entailment (CLTE) tries to detect the entailment relationship between two text fragments in different languages. We solved this problem in three steps. Firstly, we use a off-the-shelf machine translation (MT) tool to convert the two input texts into the same language. Then after performing a text preprocessing, we extract multiple feature types with respect to surface text and grammar. We also propose novel feature types regarding to sentence difference and semantic similarity based on our observations in the preliminary experiments. Finally, we adopt a multiclass SVM algorithm for classification. The results on the cross-lingual data collections provided by SemEval 2013 show that (1) we can build portable and effective systems across languages using MT and multiple effective features; (2) our systems achieve the best results among the participants on two test datasets, i.e., FRA-ENG and DEU-ENG.

Original languageEnglish
Title of host publication*SEM 2013 - 2nd Joint Conference on Lexical and Computational Semantics
PublisherAssociation for Computational Linguistics (ACL)
Pages118-123
Number of pages6
ISBN (Electronic)9781937284497
StatePublished - 2013
Event2nd Joint Conference on Lexical and Computational Semantics, *SEM 2013 - Atlanta, United States
Duration: 13 Jun 201314 Jun 2013

Publication series

Name*SEM 2013 - 2nd Joint Conference on Lexical and Computational Semantics
Volume2

Conference

Conference2nd Joint Conference on Lexical and Computational Semantics, *SEM 2013
Country/TerritoryUnited States
CityAtlanta
Period13/06/1314/06/13

Fingerprint

Dive into the research topics of 'ECNUCS: Recognizing cross-lingual textual entailment using multiple text similarity and text difference measures'. Together they form a unique fingerprint.

Cite this