Recognizing Textual Entailment by Soft Dependency Tree Matching

We present a rule - based method for recognizing entailmen t relation between a pair of text fragments by comparing their dependency tree structures. We used a dependency parser to generate the dependency triple s of the text – hypothesis pair s . A dependency triple is a n arc in the dependency par...

ver descrição completa

Detalhes bibliográficos
Autores: Rohini Basak, Sudip Kumar Naskar, Partha Pakray, Alexander Gelbukh
Formato: artículo
Estado:Versión publicada
Fecha de publicación:2015
País:México
Recursos:Instituto Politécnico Nacional
Repositorio:Redalyc-IPN
OAI Identifier:oai:redalyc.org:61543181006
Acesso em linha:https://www.redalyc.org/articulo.oa?id=61543181006
Access Level:acceso abierto
Palavra-chave:Computación
rules
PETE dataset
Textual entailment
dependency parsing
dependency relation matching
id MX_bbb9b47f991979c2e7145f752d9ff8bb
oai_identifier_str oai:redalyc.org:61543181006
network_acronym_str MX
network_name_str México
repository_id_str
spelling Recognizing Textual Entailment by Soft Dependency Tree MatchingRohini BasakSudip Kumar NaskarPartha PakrayAlexander GelbukhComputaciónrulesPETE datasetTextual entailmentdependency parsingdependency relation matchingWe present a rule - based method for recognizing entailmen t relation between a pair of text fragments by comparing their dependency tree structures. We used a dependency parser to generate the dependency triple s of the text – hypothesis pair s . A dependency triple is a n arc in the dependency parse tree. Each triple in the hypothesis is checked against all the triple s in the text to find a matching pair . We have developed a number of matching rules after a detailed analysis of the PETE dataset , which we used for the experiments . A successful match satisfying any of th ese rules assign s a matching score of 1 to the child node of th at particular arc in the hypothesis dependency tree. Then the dependency parse tree is traversed in post - order way to obtain the final entai lment score at the root node. The score s of the leaf nodes are propagated from the bottom of the tree to the non - leaf nodes , up to the root node. The entailment score of the root node is compared against a predefined threshold value to make the entailment decision . Experimental result s on the PETE dataset sh ow an accuracy of 87.69 % on the dev elopment set and 73. 75 % on the test set , which outperforms the state - of - the - art results reported on this dataset so far . We did not use any other NLP tools or knowledge sources , to emphasize the role of dependency parsing in rec ognizing textual entailment.Instituto Politécnico Nacional2015info:eu-repo/semantics/publishedVersioninfo:eu-repo/semantics/articleapplication/pdf1405-5546https://www.redalyc.org/articulo.oa?id=61543181006Computación y Sistemas (México) Num.4 Vol.19reponame:Redalyc-IPNinstname:Instituto Politécnico Nacionalinstacron:IPNenhttp://www.redalyc.org/revista.oa?id=615Computación y Sistemasinfo:eu-repo/semantics/openAccessoai:redalyc.org:615431810062026-01-29T02:55:26Z
dc.title.none.fl_str_mv Recognizing Textual Entailment by Soft Dependency Tree Matching
title Recognizing Textual Entailment by Soft Dependency Tree Matching
spellingShingle Recognizing Textual Entailment by Soft Dependency Tree Matching
Rohini Basak
Computación
rules
PETE dataset
Textual entailment
dependency parsing
dependency relation matching
title_short Recognizing Textual Entailment by Soft Dependency Tree Matching
title_full Recognizing Textual Entailment by Soft Dependency Tree Matching
title_fullStr Recognizing Textual Entailment by Soft Dependency Tree Matching
title_full_unstemmed Recognizing Textual Entailment by Soft Dependency Tree Matching
title_sort Recognizing Textual Entailment by Soft Dependency Tree Matching
dc.creator.none.fl_str_mv Rohini Basak
Sudip Kumar Naskar
Partha Pakray
Alexander Gelbukh
author Rohini Basak
author_facet Rohini Basak
Sudip Kumar Naskar
Partha Pakray
Alexander Gelbukh
author_role author
author2 Sudip Kumar Naskar
Partha Pakray
Alexander Gelbukh
author2_role author
author
author
dc.subject.none.fl_str_mv Computación
rules
PETE dataset
Textual entailment
dependency parsing
dependency relation matching
topic Computación
rules
PETE dataset
Textual entailment
dependency parsing
dependency relation matching
description We present a rule - based method for recognizing entailmen t relation between a pair of text fragments by comparing their dependency tree structures. We used a dependency parser to generate the dependency triple s of the text – hypothesis pair s . A dependency triple is a n arc in the dependency parse tree. Each triple in the hypothesis is checked against all the triple s in the text to find a matching pair . We have developed a number of matching rules after a detailed analysis of the PETE dataset , which we used for the experiments . A successful match satisfying any of th ese rules assign s a matching score of 1 to the child node of th at particular arc in the hypothesis dependency tree. Then the dependency parse tree is traversed in post - order way to obtain the final entai lment score at the root node. The score s of the leaf nodes are propagated from the bottom of the tree to the non - leaf nodes , up to the root node. The entailment score of the root node is compared against a predefined threshold value to make the entailment decision . Experimental result s on the PETE dataset sh ow an accuracy of 87.69 % on the dev elopment set and 73. 75 % on the test set , which outperforms the state - of - the - art results reported on this dataset so far . We did not use any other NLP tools or knowledge sources , to emphasize the role of dependency parsing in rec ognizing textual entailment.
publishDate 2015
dc.date.none.fl_str_mv 2015
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 1405-5546
https://www.redalyc.org/articulo.oa?id=61543181006
identifier_str_mv 1405-5546
url https://www.redalyc.org/articulo.oa?id=61543181006
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=615
dc.rights.none.fl_str_mv Computación y Sistemas
info:eu-repo/semantics/openAccess
rights_invalid_str_mv Computación y Sistemas
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 Computación y Sistemas (México) Num.4 Vol.19
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_ 1858176745484582912
score 14.965132

Registos relacionados