Semantic Textual Entailment Recognition using UNL

A two-way textual entailment (TE) recognition system that uses semantic features has been described in this paper. We have used the Universal Networking Language (UNL) to identify the semantic features. UNL has all the components of a natural language. The development of a UNL based textual entailme...

Descripción completa

Detalles Bibliográficos
Autores: Partha Pakray, Soujanya Poria, Sivaji Bandyopadhyay, Alexander Gelbukh
Tipo de recurso: artículo
Estado:Versión publicada
Fecha de publicación:2011
País:México
Institución:Instituto Politécnico Nacional
Repositorio:Redalyc-IPN
OAI Identifier:oai:redalyc.org:402640456003
Acceso en línea:https://www.redalyc.org/articulo.oa?id=402640456003
Access Level:acceso abierto
Palabra clave:Computación
RTE
4 Test Data
Textual Entailment
3 Test Annotated Data
Universal Networking Language (UNL)
id MX_8f6b3df9c4e0134e41c092f196c48278
oai_identifier_str oai:redalyc.org:402640456003
network_acronym_str MX
network_name_str México
repository_id_str
spelling Semantic Textual Entailment Recognition using UNLPartha PakraySoujanya PoriaSivaji BandyopadhyayAlexander GelbukhComputaciónRTE4 Test DataTextual Entailment3 Test Annotated DataUniversal Networking Language (UNL)A two-way textual entailment (TE) recognition system that uses semantic features has been described in this paper. We have used the Universal Networking Language (UNL) to identify the semantic features. UNL has all the components of a natural language. The development of a UNL based textual entailment system that compares the UNL relations in both the text and the hypothesis has been reported. The semantic TE system has been developed using the RTE-3 test annotated set as a development set (includes 800 text-hypothesis pairs). Evaluation scores obtained on the RTE-4 test set (includes 1000 text-hypothesis pairs) show 55.89% precision and 65.40% recall for YES decisions and 66.50% precision and 55.20% recall for NO decisions and overall 60.3% precision and 60.3% recall.Instituto Politécnico Nacional2011info:eu-repo/semantics/publishedVersioninfo:eu-repo/semantics/articleapplication/pdf1870-9044https://www.redalyc.org/articulo.oa?id=402640456003Polibits (México) Vol.43reponame:Redalyc-IPNinstname:Instituto Politécnico Nacionalinstacron:IPNenhttp://www.redalyc.org/revista.oa?id=4026Polibitsinfo:eu-repo/semantics/openAccessoai:redalyc.org:4026404560032026-01-29T02:55:48Z
dc.title.none.fl_str_mv Semantic Textual Entailment Recognition using UNL
title Semantic Textual Entailment Recognition using UNL
spellingShingle Semantic Textual Entailment Recognition using UNL
Partha Pakray
Computación
RTE
4 Test Data
Textual Entailment
3 Test Annotated Data
Universal Networking Language (UNL)
title_short Semantic Textual Entailment Recognition using UNL
title_full Semantic Textual Entailment Recognition using UNL
title_fullStr Semantic Textual Entailment Recognition using UNL
title_full_unstemmed Semantic Textual Entailment Recognition using UNL
title_sort Semantic Textual Entailment Recognition using UNL
dc.creator.none.fl_str_mv Partha Pakray
Soujanya Poria
Sivaji Bandyopadhyay
Alexander Gelbukh
author Partha Pakray
author_facet Partha Pakray
Soujanya Poria
Sivaji Bandyopadhyay
Alexander Gelbukh
author_role author
author2 Soujanya Poria
Sivaji Bandyopadhyay
Alexander Gelbukh
author2_role author
author
author
dc.subject.none.fl_str_mv Computación
RTE
4 Test Data
Textual Entailment
3 Test Annotated Data
Universal Networking Language (UNL)
topic Computación
RTE
4 Test Data
Textual Entailment
3 Test Annotated Data
Universal Networking Language (UNL)
description A two-way textual entailment (TE) recognition system that uses semantic features has been described in this paper. We have used the Universal Networking Language (UNL) to identify the semantic features. UNL has all the components of a natural language. The development of a UNL based textual entailment system that compares the UNL relations in both the text and the hypothesis has been reported. The semantic TE system has been developed using the RTE-3 test annotated set as a development set (includes 800 text-hypothesis pairs). Evaluation scores obtained on the RTE-4 test set (includes 1000 text-hypothesis pairs) show 55.89% precision and 65.40% recall for YES decisions and 66.50% precision and 55.20% recall for NO decisions and overall 60.3% precision and 60.3% recall.
publishDate 2011
dc.date.none.fl_str_mv 2011
dc.type.none.fl_str_mv info:eu-repo/semantics/publishedVersion
info:eu-repo/semantics/article
format article
status_str publishedVersion
dc.identifier.none.fl_str_mv 1870-9044
https://www.redalyc.org/articulo.oa?id=402640456003
identifier_str_mv 1870-9044
url https://www.redalyc.org/articulo.oa?id=402640456003
dc.language.none.fl_str_mv en
language_invalid_str_mv en
dc.relation.none.fl_str_mv http://www.redalyc.org/revista.oa?id=4026
dc.rights.none.fl_str_mv Polibits
info:eu-repo/semantics/openAccess
rights_invalid_str_mv Polibits
eu_rights_str_mv openAccess
dc.format.none.fl_str_mv application/pdf
dc.publisher.none.fl_str_mv Instituto Politécnico Nacional
publisher.none.fl_str_mv Instituto Politécnico Nacional
dc.source.none.fl_str_mv Polibits (México) Vol.43
reponame:Redalyc-IPN
instname:Instituto Politécnico Nacional
instacron:IPN
instname_str Instituto Politécnico Nacional
instacron_str IPN
institution IPN
reponame_str Redalyc-IPN
collection Redalyc-IPN
repository.name.fl_str_mv
repository.mail.fl_str_mv
_version_ 1858176100855709696
score 15,30478

Similares en LA Referencia