Does Coreference Resolution Improve Aspect Based Sentiment Analysis?

Aspect-Based Sentiment Analysis (ABSA) has generally focused on extracting explicit opinion targets and classifying them into polarities and categories. Most approaches ignore implicitly expressed opinions, even though they make up a significant part of language; in fact, approximately 25% of the ta...

ver descrição completa

Detalhes bibliográficos
Autor: Ryhänen, Rosa-Maria Kristiina
Formato: tesis de maestría
Fecha de publicación:2022
País:España
Recursos:Universidad del País Vasco
Repositorio:Addi. Archivo Digital para la Docencia y la Investigación
OAI Identifier:oai:addi.ehu.eus:10810/61818
Acesso em linha:http://hdl.handle.net/10810/61818
Access Level:acceso abierto
Palavra-chave:aspect-based sentiment analysis
coreference resolution
opinion target extraction
aspect category detection
id ES_a43ca7c5bc878466ffa66ab10d5c2aef
oai_identifier_str oai:addi.ehu.eus:10810/61818
network_acronym_str ES
network_name_str España
repository_id_str
spelling Does Coreference Resolution Improve Aspect Based Sentiment Analysis?Ryhänen, Rosa-Maria Kristiinaaspect-based sentiment analysiscoreference resolutionopinion target extractionaspect category detectionAspect-Based Sentiment Analysis (ABSA) has generally focused on extracting explicit opinion targets and classifying them into polarities and categories. Most approaches ignore implicitly expressed opinions, even though they make up a significant part of language; in fact, approximately 25% of the targets in the SemEval ABSA 2016 English restaurant reviews (Pontiki et al., 2016) are implicit and are not taken into consideration when training a model. We propose to solve a part of the implicit targets with coreference resolution in order to improve two ABSA tasks: opinion target extraction and aspect category detection. Our results suggest that coreference resolution helps to perform opinion target extraction and aspect category detection, when the latter is handled as a multi-label classification task. The data and code are publicly available on GitHub https://github.com/rosamariaryh/absa-corefAgerri Gascón, RodrigoMáster Universitario en Análisis y Procesamiento del LenguajeHizkuntzaren Azterketa eta Prozesamendua Unibertsitate Masterra2023202320232022info:eu-repo/semantics/masterThesisapplication/pdfhttp://hdl.handle.net/10810/61818reponame:Addi. Archivo Digital para la Docencia y la Investigacióninstname:Universidad del País VascoInglésEspañolinfo:eu-repo/semantics/openAccess© 2022, la autoraoai:addi.ehu.eus:10810/618182026-06-18T09:23:17Z
dc.title.none.fl_str_mv Does Coreference Resolution Improve Aspect Based Sentiment Analysis?
title Does Coreference Resolution Improve Aspect Based Sentiment Analysis?
spellingShingle Does Coreference Resolution Improve Aspect Based Sentiment Analysis?
Ryhänen, Rosa-Maria Kristiina
aspect-based sentiment analysis
coreference resolution
opinion target extraction
aspect category detection
title_short Does Coreference Resolution Improve Aspect Based Sentiment Analysis?
title_full Does Coreference Resolution Improve Aspect Based Sentiment Analysis?
title_fullStr Does Coreference Resolution Improve Aspect Based Sentiment Analysis?
title_full_unstemmed Does Coreference Resolution Improve Aspect Based Sentiment Analysis?
title_sort Does Coreference Resolution Improve Aspect Based Sentiment Analysis?
dc.creator.none.fl_str_mv Ryhänen, Rosa-Maria Kristiina
author Ryhänen, Rosa-Maria Kristiina
author_facet Ryhänen, Rosa-Maria Kristiina
author_role author
dc.contributor.none.fl_str_mv Agerri Gascón, Rodrigo
Máster Universitario en Análisis y Procesamiento del Lenguaje
Hizkuntzaren Azterketa eta Prozesamendua Unibertsitate Masterra
dc.subject.none.fl_str_mv aspect-based sentiment analysis
coreference resolution
opinion target extraction
aspect category detection
topic aspect-based sentiment analysis
coreference resolution
opinion target extraction
aspect category detection
description Aspect-Based Sentiment Analysis (ABSA) has generally focused on extracting explicit opinion targets and classifying them into polarities and categories. Most approaches ignore implicitly expressed opinions, even though they make up a significant part of language; in fact, approximately 25% of the targets in the SemEval ABSA 2016 English restaurant reviews (Pontiki et al., 2016) are implicit and are not taken into consideration when training a model. We propose to solve a part of the implicit targets with coreference resolution in order to improve two ABSA tasks: opinion target extraction and aspect category detection. Our results suggest that coreference resolution helps to perform opinion target extraction and aspect category detection, when the latter is handled as a multi-label classification task. The data and code are publicly available on GitHub https://github.com/rosamariaryh/absa-coref
publishDate 2022
dc.date.none.fl_str_mv 2022
2023
2023
2023
dc.type.none.fl_str_mv info:eu-repo/semantics/masterThesis
format masterThesis
dc.identifier.none.fl_str_mv http://hdl.handle.net/10810/61818
url http://hdl.handle.net/10810/61818
dc.language.none.fl_str_mv Inglés
Español
language_invalid_str_mv Inglés
Español
dc.rights.none.fl_str_mv info:eu-repo/semantics/openAccess
© 2022, la autora
eu_rights_str_mv openAccess
rights_invalid_str_mv © 2022, la autora
dc.format.none.fl_str_mv application/pdf
dc.source.none.fl_str_mv reponame:Addi. Archivo Digital para la Docencia y la Investigación
instname:Universidad del País Vasco
instname_str Universidad del País Vasco
reponame_str Addi. Archivo Digital para la Docencia y la Investigación
collection Addi. Archivo Digital para la Docencia y la Investigación
repository.name.fl_str_mv
repository.mail.fl_str_mv
_version_ 1869415480579588096
score 15.301603

Registos relacionados