SOFTCARDINALITY: Learning to identify directional cross-lingual entailment from cardinalities and SMT

Sergio Jimenez, Claudia Becerra, Alexander Gelbukh

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

6 Scopus citations

Abstract

In this paper we describe our system submitted for evaluation in the CLTE-SemEval-2013 task, which achieved the best results in two of the four data sets, and finished third in average. This system consists of a SVM classifier with features extracted from texts (and their translations SMT) based on a cardinality function. Such function was the soft cardinality. Furthermore, this system was simplified by providing a single model for the 4 pairs of languages obtaining better (unofficial) results than separate models for each language pair. We also evaluated the use of additional circular-pivoting translations achieving results 6.14% above the best official results.

Original languageEnglish
Title of host publication*SEM 2013 - 2nd Joint Conference on Lexical and Computational Semantics
PublisherAssociation for Computational Linguistics (ACL)
Pages34-38
Number of pages5
ISBN (Electronic)9781937284497
StatePublished - 2013
Externally publishedYes
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 'SOFTCARDINALITY: Learning to identify directional cross-lingual entailment from cardinalities and SMT'. Together they form a unique fingerprint.

Cite this