Context aware semantic adaptation network for cross domain implicit sentiment classification

Abstract Cross-domain sentiment classification could be attributed to two steps. The first step is used to extract the text representation, and the other is to reduce domain discrepancy. Existing methods mostly focus on learning the domain-invariant information, rarely consider using the domain-spec...

Descripción completa

Guardado en:

Detalles Bibliográficos
Autores principales:	Enguang Zuo, Alimjan Aysa, Mahpirat Muhammat, Yuxia Zhao, Kurban Ubul
Formato:	article
Lenguaje:	EN
Publicado:	Nature Portfolio 2021
Materias:	Medicine R Science Q
Acceso en línea:	https://doaj.org/article/837ce806c46d40efbe70da830d4abdee
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

id	oai:doaj.org-article:837ce806c46d40efbe70da830d4abdee
record_format	dspace
spelling	oai:doaj.org-article:837ce806c46d40efbe70da830d4abdee2021-11-14T12:19:07ZContext aware semantic adaptation network for cross domain implicit sentiment classification10.1038/s41598-021-01385-12045-2322https://doaj.org/article/837ce806c46d40efbe70da830d4abdee2021-11-01T00:00:00Zhttps://doi.org/10.1038/s41598-021-01385-1https://doaj.org/toc/2045-2322Abstract Cross-domain sentiment classification could be attributed to two steps. The first step is used to extract the text representation, and the other is to reduce domain discrepancy. Existing methods mostly focus on learning the domain-invariant information, rarely consider using the domain-specific semantic information, which could help cross-domain sentiment classification; traditional adversarial-based models merely focus on aligning the global distribution ignore maximizing the class-specific decision boundaries. To solve these problems, we propose a context-aware semantic adaptation (CASA) network for cross-domain implicit sentiment classification (ISC). CASA can provide more semantic relationships and an accurate understanding of the emotion-changing process for ISC tasks lacking explicit emotion words. (1) To obtain inter- and intrasentence semantic associations, our model builds a context-aware heterogeneous graph (CAHG), which can aggregate the intrasentence dependency information and the intersentence node interaction information, followed by an attention mechanism that remains high-level domain-specific features. (2) Moreover, we conduct a new multigrain discriminator (MGD) to effectively reduce the interdomain distribution discrepancy and improve intradomain class discrimination. Experimental results demonstrate the effectiveness of different modules compared with existing models on the Chinese implicit emotion dataset and four public explicit datasets.Enguang ZuoAlimjan AysaMahpirat MuhammatYuxia ZhaoKurban UbulNature PortfolioarticleMedicineRScienceQENScientific Reports, Vol 11, Iss 1, Pp 1-14 (2021)
institution	DOAJ
collection	DOAJ
language	EN
topic	Medicine R Science Q
spellingShingle	Medicine R Science Q Enguang Zuo Alimjan Aysa Mahpirat Muhammat Yuxia Zhao Kurban Ubul Context aware semantic adaptation network for cross domain implicit sentiment classification
description	Abstract Cross-domain sentiment classification could be attributed to two steps. The first step is used to extract the text representation, and the other is to reduce domain discrepancy. Existing methods mostly focus on learning the domain-invariant information, rarely consider using the domain-specific semantic information, which could help cross-domain sentiment classification; traditional adversarial-based models merely focus on aligning the global distribution ignore maximizing the class-specific decision boundaries. To solve these problems, we propose a context-aware semantic adaptation (CASA) network for cross-domain implicit sentiment classification (ISC). CASA can provide more semantic relationships and an accurate understanding of the emotion-changing process for ISC tasks lacking explicit emotion words. (1) To obtain inter- and intrasentence semantic associations, our model builds a context-aware heterogeneous graph (CAHG), which can aggregate the intrasentence dependency information and the intersentence node interaction information, followed by an attention mechanism that remains high-level domain-specific features. (2) Moreover, we conduct a new multigrain discriminator (MGD) to effectively reduce the interdomain distribution discrepancy and improve intradomain class discrimination. Experimental results demonstrate the effectiveness of different modules compared with existing models on the Chinese implicit emotion dataset and four public explicit datasets.
format	article
author	Enguang Zuo Alimjan Aysa Mahpirat Muhammat Yuxia Zhao Kurban Ubul
author_facet	Enguang Zuo Alimjan Aysa Mahpirat Muhammat Yuxia Zhao Kurban Ubul
author_sort	Enguang Zuo
title	Context aware semantic adaptation network for cross domain implicit sentiment classification
title_short	Context aware semantic adaptation network for cross domain implicit sentiment classification
title_full	Context aware semantic adaptation network for cross domain implicit sentiment classification
title_fullStr	Context aware semantic adaptation network for cross domain implicit sentiment classification
title_full_unstemmed	Context aware semantic adaptation network for cross domain implicit sentiment classification
title_sort	context aware semantic adaptation network for cross domain implicit sentiment classification
publisher	Nature Portfolio
publishDate	2021
url	https://doaj.org/article/837ce806c46d40efbe70da830d4abdee
work_keys_str_mv	AT enguangzuo contextawaresemanticadaptationnetworkforcrossdomainimplicitsentimentclassification AT alimjanaysa contextawaresemanticadaptationnetworkforcrossdomainimplicitsentimentclassification AT mahpiratmuhammat contextawaresemanticadaptationnetworkforcrossdomainimplicitsentimentclassification AT yuxiazhao contextawaresemanticadaptationnetworkforcrossdomainimplicitsentimentclassification AT kurbanubul contextawaresemanticadaptationnetworkforcrossdomainimplicitsentimentclassification
_version_	1718429297772855296

Context aware semantic adaptation network for cross domain implicit sentiment classification

Ejemplares similares