A Dual-Template Prompted Mutual Learning Generative Model for Implicit Aspect-Based Sentiment Analysis

Generative models have shown excellent results in aspect-based sentiment analysis tasks by predicting quadruples by setting specific template formats. The existing research predicts sentiment elements and enhances the dependency between elements using the multi-template prompting method, but it does...

Full description

Saved in:
Bibliographic Details
Main Authors: Zhou Lei, Yawei Zhang, Shengbo Chen
Format: Article
Language:English
Published: MDPI AG 2024-09-01
Series:Applied Sciences
Subjects:
Online Access:https://www.mdpi.com/2076-3417/14/19/8719
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850283832377344000
author Zhou Lei
Yawei Zhang
Shengbo Chen
author_facet Zhou Lei
Yawei Zhang
Shengbo Chen
author_sort Zhou Lei
collection DOAJ
description Generative models have shown excellent results in aspect-based sentiment analysis tasks by predicting quadruples by setting specific template formats. The existing research predicts sentiment elements and enhances the dependency between elements using the multi-template prompting method, but it does not realize the information interaction in the generation process, and it ignores the dependency between the prompt template and the aspect terms and opinion terms in the input sequence. In this paper, we propose a Dual-template Prompted Mutual Learning (DPML) generative model to enhance the information interaction between generation modules. Specifically, this paper designs a dual template based on prompt learning and, at the same time, develops a mutual learning information enhancement module to guide each generated training process to interact with iterative information. Secondly, in the decoding stage, a label marking the interactive learning module is added to share the explicit emotional expression in the sequence, which can enhance the ability of the model to capture implicit emotion. On two public datasets, our model achieves an average improvement of 5.3% and 3.4% in F1 score compared with the previous state-of-the-art model. In the implicit sentiment analysis experiment, the F1 score of the proposed model in the data subset containing implicit words is increased by 2.75% and 3.42%, respectively.
format Article
id doaj-art-9ce148c7aac847baab334a04d833fa48
institution OA Journals
issn 2076-3417
language English
publishDate 2024-09-01
publisher MDPI AG
record_format Article
series Applied Sciences
spelling doaj-art-9ce148c7aac847baab334a04d833fa482025-08-20T01:47:41ZengMDPI AGApplied Sciences2076-34172024-09-011419871910.3390/app14198719A Dual-Template Prompted Mutual Learning Generative Model for Implicit Aspect-Based Sentiment AnalysisZhou Lei0Yawei Zhang1Shengbo Chen2School of Computer Engineering and Science, Shanghai University, Shanghai 200444, ChinaSchool of Computer Engineering and Science, Shanghai University, Shanghai 200444, ChinaSchool of Computer Engineering and Science, Shanghai University, Shanghai 200444, ChinaGenerative models have shown excellent results in aspect-based sentiment analysis tasks by predicting quadruples by setting specific template formats. The existing research predicts sentiment elements and enhances the dependency between elements using the multi-template prompting method, but it does not realize the information interaction in the generation process, and it ignores the dependency between the prompt template and the aspect terms and opinion terms in the input sequence. In this paper, we propose a Dual-template Prompted Mutual Learning (DPML) generative model to enhance the information interaction between generation modules. Specifically, this paper designs a dual template based on prompt learning and, at the same time, develops a mutual learning information enhancement module to guide each generated training process to interact with iterative information. Secondly, in the decoding stage, a label marking the interactive learning module is added to share the explicit emotional expression in the sequence, which can enhance the ability of the model to capture implicit emotion. On two public datasets, our model achieves an average improvement of 5.3% and 3.4% in F1 score compared with the previous state-of-the-art model. In the implicit sentiment analysis experiment, the F1 score of the proposed model in the data subset containing implicit words is increased by 2.75% and 3.42%, respectively.https://www.mdpi.com/2076-3417/14/19/8719implicit sentiment analysisprompt learningmutual learning
spellingShingle Zhou Lei
Yawei Zhang
Shengbo Chen
A Dual-Template Prompted Mutual Learning Generative Model for Implicit Aspect-Based Sentiment Analysis
Applied Sciences
implicit sentiment analysis
prompt learning
mutual learning
title A Dual-Template Prompted Mutual Learning Generative Model for Implicit Aspect-Based Sentiment Analysis
title_full A Dual-Template Prompted Mutual Learning Generative Model for Implicit Aspect-Based Sentiment Analysis
title_fullStr A Dual-Template Prompted Mutual Learning Generative Model for Implicit Aspect-Based Sentiment Analysis
title_full_unstemmed A Dual-Template Prompted Mutual Learning Generative Model for Implicit Aspect-Based Sentiment Analysis
title_short A Dual-Template Prompted Mutual Learning Generative Model for Implicit Aspect-Based Sentiment Analysis
title_sort dual template prompted mutual learning generative model for implicit aspect based sentiment analysis
topic implicit sentiment analysis
prompt learning
mutual learning
url https://www.mdpi.com/2076-3417/14/19/8719
work_keys_str_mv AT zhoulei adualtemplatepromptedmutuallearninggenerativemodelforimplicitaspectbasedsentimentanalysis
AT yaweizhang adualtemplatepromptedmutuallearninggenerativemodelforimplicitaspectbasedsentimentanalysis
AT shengbochen adualtemplatepromptedmutuallearninggenerativemodelforimplicitaspectbasedsentimentanalysis
AT zhoulei dualtemplatepromptedmutuallearninggenerativemodelforimplicitaspectbasedsentimentanalysis
AT yaweizhang dualtemplatepromptedmutuallearninggenerativemodelforimplicitaspectbasedsentimentanalysis
AT shengbochen dualtemplatepromptedmutuallearninggenerativemodelforimplicitaspectbasedsentimentanalysis