Cargando…
Position-Enhanced Multi-Head Self-Attention Based Bidirectional Gated Recurrent Unit for Aspect-Level Sentiment Classification
Aspect-level sentiment classification (ASC) is an interesting and challenging research task to identify the sentiment polarities of aspect words in sentences. Previous attention-based methods rarely consider the position information of aspect and contextual words. For an aspect word in a sentence, i...
Autores principales: | , , , , |
---|---|
Formato: | Online Artículo Texto |
Lenguaje: | English |
Publicado: |
Frontiers Media S.A.
2022
|
Materias: | |
Acceso en línea: | https://www.ncbi.nlm.nih.gov/pmc/articles/PMC8822055/ https://www.ncbi.nlm.nih.gov/pubmed/35145460 http://dx.doi.org/10.3389/fpsyg.2021.799926 |
_version_ | 1784646529961689088 |
---|---|
author | Li, Xianyong Ding, Li Du, Yajun Fan, Yongquan Shen, Fashan |
author_facet | Li, Xianyong Ding, Li Du, Yajun Fan, Yongquan Shen, Fashan |
author_sort | Li, Xianyong |
collection | PubMed |
description | Aspect-level sentiment classification (ASC) is an interesting and challenging research task to identify the sentiment polarities of aspect words in sentences. Previous attention-based methods rarely consider the position information of aspect and contextual words. For an aspect word in a sentence, its adjacent words should be given more attention than the long distant words. Based on this consideration, this article designs a position influence vector to represent the position information between an aspect word and the context. By combining the position influence vector, multi-head self-attention mechanism and bidirectional gated recurrent unit (BiGRU), a position-enhanced multi-head self-attention network based BiGRU (PMHSAT-BiGRU) model is proposed. To verify the effectiveness of the proposed model, this article makes a large number of experiments on SemEval2014 restaurant, SemEval2014 laptop, SemEval2015 restaurant, and SemEval2016 restaurant data sets. The experiment results show that the performance of the proposed PMHSAT-BiGRU model is obviously better than the baselines. Specially, compared with the original LSTM model, the Accuracy values of the proposed PMHSAT-BiGRU model on the four data sets are improved by 5.72, 6.06, 4.52, and 3.15%, respectively. |
format | Online Article Text |
id | pubmed-8822055 |
institution | National Center for Biotechnology Information |
language | English |
publishDate | 2022 |
publisher | Frontiers Media S.A. |
record_format | MEDLINE/PubMed |
spelling | pubmed-88220552022-02-09 Position-Enhanced Multi-Head Self-Attention Based Bidirectional Gated Recurrent Unit for Aspect-Level Sentiment Classification Li, Xianyong Ding, Li Du, Yajun Fan, Yongquan Shen, Fashan Front Psychol Psychology Aspect-level sentiment classification (ASC) is an interesting and challenging research task to identify the sentiment polarities of aspect words in sentences. Previous attention-based methods rarely consider the position information of aspect and contextual words. For an aspect word in a sentence, its adjacent words should be given more attention than the long distant words. Based on this consideration, this article designs a position influence vector to represent the position information between an aspect word and the context. By combining the position influence vector, multi-head self-attention mechanism and bidirectional gated recurrent unit (BiGRU), a position-enhanced multi-head self-attention network based BiGRU (PMHSAT-BiGRU) model is proposed. To verify the effectiveness of the proposed model, this article makes a large number of experiments on SemEval2014 restaurant, SemEval2014 laptop, SemEval2015 restaurant, and SemEval2016 restaurant data sets. The experiment results show that the performance of the proposed PMHSAT-BiGRU model is obviously better than the baselines. Specially, compared with the original LSTM model, the Accuracy values of the proposed PMHSAT-BiGRU model on the four data sets are improved by 5.72, 6.06, 4.52, and 3.15%, respectively. Frontiers Media S.A. 2022-01-25 /pmc/articles/PMC8822055/ /pubmed/35145460 http://dx.doi.org/10.3389/fpsyg.2021.799926 Text en Copyright © 2022 Li, Ding, Du, Fan and Shen. https://creativecommons.org/licenses/by/4.0/This is an open-access article distributed under the terms of the Creative Commons Attribution License (CC BY). The use, distribution or reproduction in other forums is permitted, provided the original author(s) and the copyright owner(s) are credited and that the original publication in this journal is cited, in accordance with accepted academic practice. No use, distribution or reproduction is permitted which does not comply with these terms. |
spellingShingle | Psychology Li, Xianyong Ding, Li Du, Yajun Fan, Yongquan Shen, Fashan Position-Enhanced Multi-Head Self-Attention Based Bidirectional Gated Recurrent Unit for Aspect-Level Sentiment Classification |
title | Position-Enhanced Multi-Head Self-Attention Based Bidirectional Gated Recurrent Unit for Aspect-Level Sentiment Classification |
title_full | Position-Enhanced Multi-Head Self-Attention Based Bidirectional Gated Recurrent Unit for Aspect-Level Sentiment Classification |
title_fullStr | Position-Enhanced Multi-Head Self-Attention Based Bidirectional Gated Recurrent Unit for Aspect-Level Sentiment Classification |
title_full_unstemmed | Position-Enhanced Multi-Head Self-Attention Based Bidirectional Gated Recurrent Unit for Aspect-Level Sentiment Classification |
title_short | Position-Enhanced Multi-Head Self-Attention Based Bidirectional Gated Recurrent Unit for Aspect-Level Sentiment Classification |
title_sort | position-enhanced multi-head self-attention based bidirectional gated recurrent unit for aspect-level sentiment classification |
topic | Psychology |
url | https://www.ncbi.nlm.nih.gov/pmc/articles/PMC8822055/ https://www.ncbi.nlm.nih.gov/pubmed/35145460 http://dx.doi.org/10.3389/fpsyg.2021.799926 |
work_keys_str_mv | AT lixianyong positionenhancedmultiheadselfattentionbasedbidirectionalgatedrecurrentunitforaspectlevelsentimentclassification AT dingli positionenhancedmultiheadselfattentionbasedbidirectionalgatedrecurrentunitforaspectlevelsentimentclassification AT duyajun positionenhancedmultiheadselfattentionbasedbidirectionalgatedrecurrentunitforaspectlevelsentimentclassification AT fanyongquan positionenhancedmultiheadselfattentionbasedbidirectionalgatedrecurrentunitforaspectlevelsentimentclassification AT shenfashan positionenhancedmultiheadselfattentionbasedbidirectionalgatedrecurrentunitforaspectlevelsentimentclassification |