计算机科学

计算机科学 ›› 2026, Vol. 53 ›› Issue (2): 322-330.doi: 10.11896/jsjkx.250100061

• 人工智能 • 上一篇    下一篇

深度融合句法和语义特征的情感三元组片段级抽取方法

常轩伟1, 段利国1,2, 陈嘉昊1, 崔娟娟1, 李爱萍1   

  1. 1 太原理工大学计算机科学与技术学院(大数据学院) 山西 晋中 030600
    2 山西电子科技学院 山西 临汾 041000
  • 收稿日期:2025-01-09 修回日期:2025-04-29 发布日期:2026-02-10
  • 通讯作者: 段利国(463035793@qq.com)
  • 作者简介:(3137400769@qq.com)
  • 基金资助:
    山西省自然科学基金(202203021221234,202303021211052)

Method for Span-level Sentiment Triplet Extraction by Deeply Integrating Syntactic and Semantic
Features

CHANG Xuanwei1, DUAN Liguo1,2, CHEN Jiahao1, CUI Juanjuan1, LI Aiping1   

  1. 1 College of Computer Science and Technology(College of Data Science),Taiyuan University of Technology,Jinzhong,Shanxi 030600,China
    2 Shanxi University of Electronic Science and Technology,Linfen,Shanxi 041000,China
  • Received:2025-01-09 Revised:2025-04-29 Online:2026-02-10
  • About author:CHANG Xuanwei,born in 2002,postgraduate. His main research interest is sentiment analysis.
    DUAN Liguo,born in 1970,Ph.D,professor,master’s supervisor,is a senior member of CCF(No.15823S).His main research interest is natural language processing.
  • Supported by:
    Natural Science Foundation of Shanxi Province,China(202203021221234,202303021211052).

PDF (PC)

88

摘要： 方面情感三元组抽取旨在以三元组的形式抽取出句子中包含的方面词及其对应的观点词和情感极性。现有的抽取模型存在未能充分挖掘句子中包含的句法和语义信息、多词实体边界识别错误等问题。对此,提出了一种深度融合句法信息和语义信息的片段抽取模型(Span Extractor Incorporating Semantic and Syntax Features,SESS)。SESS通过结合自注意力机制和多通道图卷积网络,深度挖掘句法与语义特征之间的关联,提升了模型对复杂句式和多词实体的处理能力。同时,模型采用基于片段的抽取方法抽取方面词和观点词,捕捉长实体的整体语义,减少情感不一致性的问题。在标准数据集ASTE-Data-V2上进行的实验表明,SESS在F1值上优于绝大多数对比模型,尤其在复杂语句和多对一、一对多情感关系的处理上表现出色。此外,消融实验和案例分析验证了模型各个模块的有效性及其对任务性能的贡献,进一步证明了所提方法的先进性和鲁棒性。

关键词: 方面情感三元组抽取, 图卷积网络, 自注意力机制, 依存句法关系

Abstract: Aspect sentiment triple extraction aims to extract aspects and their corresponding opinion words and sentiment polarities in the form of triples from sentences.Existing extraction models suffer from issues such as insufficient exploitation of syntactic and semantic information in sentences and incorrect identification of multi-word entity boundaries.To address these issues,this paper proposes a span extraction model that deeply integrates syntactic and semantic features(Span Extractor Incorporating Semantic and Syntax Features,SESS).SESS combines self-attention mechanisms with multi-channel graph convolutional networks to deeply explore the associations between syntactic and semantic features,enhancing the model’s ability to handle complex sentence structures and multi-word entities.Additionally,the model employs a span-based extraction method to extract aspect and opinion words,capturing the overall semantics of long entities and reducing sentiment inconsistency issues.The experiments conducted on the standard dataset ASTE-Data-V2 demonstrate that SESS outperforms the vast majority of comparison models in terms of F1 score,particularly in processing complex sentences and one-to-many,many-to-one sentiment relationships.Furthermore,ablation experiments and case analysis validate the effectiveness of each module of the model and its contribution to task performance,further proving the advancement and robustness of the proposed method.

Key words: Aspect sentiment triplet extraction, Graph convolutional network, Self-attention mechanism, Dependency syntactic relationship

中图分类号: 

  • TP391
[1]CHEN Z,QIAN T Y,LI W L,et al.A Survey on Aspect-level Sentiment Analysis under Low-resource Conditions[J].Chinese Journal of Computers,2023,46(7):1445-1472.
[2]JOSHI M,CHEN D Q,LIU Y H,et al.SpanBERT:Improving Pre-training by Representing and Predicting Spans[J].Transactions of the Association for Computational Linguistics,2020,8:64-77.
[3]PENG H,XU L,BING L,et al.Knowing What,How and Why:A Near Complete Solution for Aspect-Based Sentiment Analysis[C]//Proceedings of the AAAI Conference on Artificial Intelligence.2020:8600-8607.
[4]XU L,LI H,LU W,et al.Position-Aware Tagging for Aspect Sentiment Triplet Extraction[C]//Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing(EMNLP).2020:2339-2349.
[5]WU Z,YING C,ZHAO F,et al.Grid Tagging Scheme for Aspect-oriented Fine-grained Opinion Extraction[C]//Findings of the Association for Computational Linguistics:EMNLP 2020.2020:2576-2585.
[6]XU L,CHIA Y K,BING L D.Learning Span-Level Interactions for Aspect Sentiment Triplet Extraction[C]//Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing.2021:4755-4766.
[7]ZHANG Y C,YANG Y F,LI Y H,et al.Boundary-driven table-filling for aspect sentiment triplet extraction[C]//Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing.2022:6485-6498.
[8]CHEN Y Q,ZHANG Z Q,ZHOU G Y,et al.Span-based dual-decoder framework for aspect sentiment triplet extraction[J].Neurocomputing,2022,492:211-221.
[9]CHEN Y Q,CHEN K M,SUN X,et al.A Span-level Bidirectional Network for Aspect Sentiment Triplet Extraction[C]//Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing.2022:4300-4309.
[10]VASWANI A,SHAZEER N,PARMAR N,et al.Attention is All You Need[C]//Proceedings of the 31st International Confe-rence on Neural Information Processing Systems.2017:6000-6010.
[11]MAO Y,SHEN Y,YU C,et al.A joint training dual-mrc framework for aspect based sentiment analysis[C]//Proceedings of the AAAI Conference on Artificial Intelligence.2021:13543-13551.
[12]CHEN S W,WANG Y,LIU J,et al.Bidirectional machine rea-ding comprehension for aspect sentiment triplet extraction[C]//Proceedings of the AAAI Conference on Artificial Intelligence.2021:12666-12674.
[13]MUKHERJEE R,NAYAK T,BUTALA Y,et al.PASTE:ATagging-Free Decoding Framework Using Pointer Networks for Aspect Sentiment Triplet Extraction[C]//Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing.2021:9279-9291.
[14]ZHANG W X,LI X,DENG Y,et al.Towards generative aspect-based sentiment analysis[C]//Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing.2021:504-510.
[15]YAN H,DAI J Q,JI T,et al.A Unified Generative Framework for Aspect-based Sentiment Analysis[C]//Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing.2021:2416-2429.
[16]LI Y,LIN Y D,LIN Y M,et al.A span-sharing joint extraction framework for harvesting aspect sentiment triplets[J].Know-ledge-Based Systems,2022,242:108366.
[17]KIPF T N,WELLING M.Semi-supervised classification withgraph convolutional networks[J].arXiv:1609.02907,2016.
[18]CHEN H,ZHAI Z P,FENG F X,et al.Enhanced multi-channel graph convolutional network for aspect sentiment triplet extraction[C]//Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics.2022:2974-2985.
[19]SHI L L,HAN D H,HAN J Y,et al.Dependency graph enhanced interactive attention network for aspect sentiment triplet extraction[J].Neurocomputing,2022,507:315-324.
[20]LI Y B,HE Q,ZHANG D M.Dual graph convolutional networks integrating affective knowledge and position information for aspect sentiment triplet extraction[J].Frontiers in Neurorobotics,2023,17:1193011.
[21]LI Q L,WEN W S,QIN J H.Improving span-based Aspect Sentiment Triplet Extraction with part-of-speech filtering and contrastive learning[J].Neural Networks,2024,177:106381.
[22]LI P,LI P,ZHANG K.Dual-Channel Span for Aspect Sentiment Triplet Extraction[C]//Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing.2023:248-261.
[23]ZHANG C,REN L,MA F,et al.Structural Bias for Aspect Sentiment Triplet Extraction[C]//Proceedings of the 29th International Conference on Computational Linguistics.2022:6736-6745.
[24]PENG K,JIANG L,PENG H,et al.Prompt Based Tri-Channel Graph Convolution Neural Network for Aspect Sentiment Triplet Extraction[C]//Proceedings of the 2024 SIAM International Conference on Data Mining(SDM).Society for Industrial and Applied Mathematics,2024:145-153.
[25]JIANG B X,LIANG S H,LIU P Y,et al.A semantically enhanced dual encoder for aspect sentiment triplet extraction[J].Neurocomputing,2023,562:126917.
[26]DEVLIN J,CHANG M W,LEE K,et al.BERT:Pre-training of Deep Bidirectional Transformers for Language Understanding[C]//Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics:Human Language Technologies.2019:4171-4186.
[27]DAI D W,CHEN T,XIA S Y,et al.Double embedding and bidirectional sentiment dependence detector for aspect sentiment triplet extraction[J].Knowledge-Based Systems,2022,253:109506.
[28]SUN X W,QI J T,ZHU Z F,et al.SenticNet and AbstractMeaning Representation driven Attention-Gate semantic framework for aspect sentiment triplet extraction[J].Engineering Applications of Artificial Intelligence,2025,139:109625.
[29]WANG B,JIANG B X,WANG G J,et al.Knowledge complementation based dual-table filling approach for aspect sentiment triplet extraction[J].Neurocomputing,2025,611:128625.
[30]LIU D X,DUAN L G,CUI J J,et al.A Semantic MatchingStrategy for Short Texts by Integrating Sememe Similarity Matrix and Dual-channel Word Vectors[J].Computer Science,2024,51(12):250-258.
[31]MANNING C D,SURDEANU M,BAUER J,et al.The Stanford CoreNLP natural language processing toolkit[C]//Proceedings of 52nd Annual Meeting of the Association for Computational Linguistics:System Demonstrations.2014:55-60.
[32]BAI X F,LIU P B,ZHANG Y.Investigating typed syntactic dependencies for targeted sentiment classification using graph attention neural network[J].IEEE/ACM Transactions on Audio,Speech,and Language Processing,2020,29:503-514.
[33]ZHAO X W,ZHOU Y,XU X J.Dual Encoder:Exploiting the Potential of Syntactic and Semantic for Aspect Sentiment Triplet Extraction[C]//Proceedings of the 2024 Joint International Conference on Computational Linguistics,Language Resources and Evaluation(LREC-COLING 2024).2024:5401-5413.
[34]SU G X,WU M M,HUANG Z Q,et al.Refine,align,and aggregate:multi-view linguistic features enhancement for aspect sentiment triplet extraction[C]//Findings of the Association for Computational Linguistics ACL 2024.2024:3212-3228.
Viewed
Full text


Abstract

Cited
  Shared   
  Discussed   
No Suggested Reading articles found!
渝ICP备16013121号-4
地址：重庆市两江新区洪湖西路18号    邮编：401121  
电话：023-63500828（编辑部） 023-67039612（会议/专题） 023-67039623（财务/发票）
E-mail：jsjkx12@163.com
本系统由北京玛格泰克科技发展有限公司设计开发