《计算机应用》唯一官方网站 ›› 2025, Vol. 45 ›› Issue (12): 3779-3785.DOI: 10.11772/j.issn.1001-9081.2024121863

• 人工智能 • 上一篇    下一篇

融合情感词典的多视角语言特征方面情感三元组抽取模型

张正悦1,2, 彭菊红1,2, 丁子胥1,2, 范馨予1,2, 胡长玉1,2   

  1. 1.湖北大学 人工智能学院,武汉 430062
    2.智能感知系统与安全教育部重点实验室(湖北大学),武汉 430062
  • 收稿日期:2025-01-03 修回日期:2025-03-30 接受日期:2025-04-07 发布日期:2025-04-16 出版日期:2025-12-10
  • 通讯作者: 彭菊红
  • 作者简介:张正悦(2000—),男,安徽池州人,硕士研究生,CCF会员,主要研究方向:方面级情感分析、方面情感三元组抽取
    彭菊红(1978—),女,辽宁盖州人,副教授,博士,主要研究方向:信号处理、电路建模与分析、人工智能方法
    丁子胥(1998—),男,河南信阳人,硕士研究生,主要研究方向:小样本语义分割、深度学习
    范馨予(1999—),女,河南商丘人,硕士研究生,主要研究方向:脑电信号情绪识别
    胡长玉(2002—),女,安徽六安人,硕士研究生,主要研究方向:微表情情绪识别。
  • 基金资助:
    国家自然科学基金面上项目(62377009)

Aspect sentiment triplet extraction model with multi-view linguistic features and sentiment lexicon

Zhengyue ZHANG1,2, Juhong PENG1,2, Zixu DING1,2, Xinyu FAN1,2, Changyu HU1,2   

  1. 1.School of Artificial Intelligence,Hubei University,Wuhan Hubei 430062,China
    2.Key Laboratory of Intelligent Sensing System and Security,Ministry of Education (Hubei University),Wuhan Hubei 430062,China
  • Received:2025-01-03 Revised:2025-03-30 Accepted:2025-04-07 Online:2025-04-16 Published:2025-12-10
  • Contact: Juhong PENG
  • About author:ZHANG Zhengyue, born in 2000, M. S. candidate. His research interests include aspect-based sentiment analysis, aspect sentiment triplet extraction.
    PENG Juhong, born in 1978, Ph. D., associate professor. Her research interests include signal processing, circuit modeling and analysis, artificial intelligence methods.
    DING Zixu, born in 1998, M. S. candidate. His research interests include few-shot semantic segmentation, deep learning.
    FAN Xinyu, born in 1999, M. S. candidate. Her research interests include EGG signal emotion recognition.
    HU Changyu, born in 2002, M. S. candidate. Her research interests include micro-expression emotion recognition.
  • Supported by:
    General Program of National Natural Science Foundation of China(62377009)

摘要:

在自然语言处理(NLP)任务中,方面情感三元组抽取(ASTE)旨在识别文本中方面词、观点词和情感极性之间的联系,是实现细粒度情感分析的关键步骤。在当前的主流方法中,端到端模型普遍存在对语言特征理解不足以及对情感表达稀疏性处理不佳的问题,进而限制了模型的准确性和鲁棒性,而管道式模型存在传播错误问题。针对上述问题,提出一种融合情感词典的多视角语言特征ASTE模型(MVLF-SL)。在MVLF-SL中,多视角语言特征能够帮助模型理解上下文和隐含语义,而情感词典能够提供额外的情感先验知识。首先,利用图卷积网络(GCN)对多视角语言特征进行特征表达,并得到增强的语言特征;其次,使用动态融合策略将增强的语言特征与情感词典相融合;再次,利用多层GCN结合邻接关系和节点特征增强方面词和观点词的特征表示;最后,利用双仿射注意力(BA)机制改进的边界驱动的表格填充(BDTF)方法对三元组进行解码和抽取。实验结果表明,在ASTE-DATA-V2数据集的4个子数据集14res、14lap、15res和16res上,相较于BDTF模型,MVLF-SL的F1分数分别提升了0.57、2.08、2.20、1.74个百分点。可见,所提模型能在ASTE上取得更好的表现,并充分利用了语言特征和外部情感知识。

关键词: 方面情感三元组抽取, 句法依赖关系, 词性信息, 句法依赖距离, 图卷积网络

Abstract:

In Natural Language Processing (NLP) tasks, Aspect Sentiment Triplet Extraction (ASTE) aims to identify the relationships among aspect terms, opinion terms, and sentiment polarity in text, serving as a crucial step in realizing fine-grained sentiment analysis. In current mainstream methods, end-to-end models generally suffer from insufficient understanding of linguistic features and poor handling of the sparsity in sentiment expressions, which limits models’ accuracy and robustness. At the same time, pipeline models are prone to error propagation. To address these issues, an ASTE model with Multi-View Linguistic Features and Sentiment Lexicon (MVLF-SL) was proposed. In this model, multi-view linguistic features were utilized to enhance the model’s ability to understand context and implicit semantics, while additional prior knowledge of sentiment was provided by a sentiment lexicon. Firstly, Graph Convolutional Network (GCN) was used to represent multi-view linguistic features and obtain enhanced linguistic features. Secondly, a dynamic fusion strategy was adopted to integrate the enhanced linguistic features with the sentiment lexicon. Thirdly, multi-layer GCN was employed to enhance the feature representations of aspect and opinion terms by incorporating adjacency relations and node features. Finally, a Boundary-Driven Table-Filling (BDTF) method, improved with a Biaffine Attention (BA) mechanism, was used for decoding and extracting the triplets. Experimental results on four subsets (14res, 14lap, 15res, and 16res) of the ASTE-DATA-V2 dataset show that compared with the BDTF model, MVLF-SL has the F1-scores improved by 0.57, 2.08, 2.20, and 1.74 percentage points, respectively. It can be seen that the proposed model achieves better performance in ASTE, and fully utilizes linguistic features and external sentiment knowledge.

Key words: Aspect Sentiment Triplet Extraction (ASTE), syntactic dependency relation, part-of-speech information, syntactic dependency distance, Graph Convolutional Network (GCN)

中图分类号: