《计算机应用》唯一官方网站 ›› 2023, Vol. 43 ›› Issue (6): 1796-1802.DOI: 10.11772/j.issn.1001-9081.2022060891

• 人工智能 • 上一篇    下一篇

融合多窗口局部信息的方面级情感分析模型

郑智雄1,2, 刘建华1,2(), 孙水华1,2, 徐戈3, 林鸿辉1,2   

  1. 1.福建工程学院 计算机科学与数学学院,福州 350118
    2.福建省大数据挖掘与应用技术重点实验室(福建工程学院),福州 350118
    3.闽江学院 计算机与控制工程学院,福州 350108
  • 收稿日期:2022-06-20 修回日期:2022-09-23 接受日期:2022-10-11 发布日期:2022-11-07 出版日期:2023-06-10
  • 通讯作者: 刘建华
  • 作者简介:郑智雄(1996—),男,福建莆田人,硕士研究生,CCF会员,主要研究方向:方面级情感分析
    刘建华(1967—),男,江西吉安人,教授,博士,CCF会员,主要研究方向:智能计算、机器学习Email:jhliu@fjnu.edu.cn
    孙水华(1962—),女,福建宁德人,教授,博士,主要研究方向:自然语言处理、机器翻译
    徐戈(1978—),男,浙江淳安人,教授,博士,CCF会员,主要研究方向:智能问答机器人、情感分析
    林鸿辉(1996—),男,福建福州人,硕士研究生,CCF会员,主要研究方向:自然语言处理。
  • 基金资助:
    国家自然科学基金资助项目(62172095);福州市科技创新平台项目(2021?P?052);福建工程学院发展基金资助项目(GY?Z20046);中央引导地方项目(2020L3024)

Aspect-based sentiment analysis model fused with multi-window local information

Zhixiong ZHENG1,2, Jianhua LIU1,2(), Shuihua SUN1,2, Ge XU3, Honghui LIN1,2   

  1. 1.College of Computer Science and Mathematics,Fujian University of Technology,Fuzhou Fujian 350118,China
    2.Fujian Provincial Key Laboratory of Big Data Mining and Applications (Fujian University of Technology),Fuzhou Fujian 350118,China
    3.College of Computer and Control Engineering,Minjiang University,Fuzhou Fujian 350108,China
  • Received:2022-06-20 Revised:2022-09-23 Accepted:2022-10-11 Online:2022-11-07 Published:2023-06-10
  • Contact: Jianhua LIU
  • About author:ZHENG Zhixiong, born in 1996, M. S. candidate. His research interests include aspect-based sentiment analysis.
    SUN Shuihua, born in 1962, Ph. D., professor. Her research interests include natural language processing, machine translation.
    XU Ge, born in 1978, Ph. D., professor. His research interests include intelligent quiz bot, sentiment analysis.
    LIN Honghui, born in 1996, M. S. candidate. His research interests include natural language processing.
  • Supported by:
    National Natural Science Foundation of China(62172095);Fuzhou Science and Technology Innovation Platform Program(2021-P-052);Fujian University of Technology Development Foundation(GY-Z20046);Central Leading Local Project of China(2020L3024)

摘要:

针对目前方面级情感分析(ABSA)模型过多依赖关系较为稀疏的句法依赖树学习特征表示,导致模型学习局部信息能力不足的问题,提出了一种融合多窗口局部信息的ABSA模型MWGAT(combining Multi-Window local information and Graph ATtention network)。首先,通过多窗口局部特征学习机制学习局部上下文特征,并挖掘文本包含的潜在局部信息;其次,采用能够较好理解依赖树的图注意力网络(GAT)学习句法依赖树所表示的语法结构信息,并生成语法感知的上下文特征;最后,将这两种表示不同语义信息的特征融合,形成既包含句法依赖树的语法信息又包含局部信息的特征表示,从而便于分类器高效判别方面词的情感极性。在Restaurant、Laptop和Twitter这3个公开数据集上进行实验,结果表明与结合了句法依赖树的T-GCN(Type-aware Graph Convolutional Network)模型相比,所提模型的Macro-F1分数分别提高了2.48%、2.37%和0.32%。可见,所提模型能够有效挖掘潜在的局部信息,并更为精确地预测方面词的情感极性。

关键词: 图神经网络, 注意力机制, 方面级情感分析, 局部特征学习, 图注意力网络, 门控机制

Abstract:

Focused on the issue that the current Aspect-Based Sentiment Analysis (ABSA) models rely too much on the syntactic dependency tree with relatively sparse relationships to learn feature representations, which leads to the insufficient ability of the model to learn local information, an ABSA model fused with multi-window local information called MWGAT (combining Multi-Window local information and Graph ATtention network) was proposed. Firstly, the local contextual features were learned through the multi-window local feature learning mechanism, and the potential local information contained in the text was mined. Secondly, Graph ATtention network (GAT), which can better understand the syntactic dependency tree, was used to learn the syntactic structure information represented by the syntactic dependency tree, and syntax-aware contextual features were generated. Finally, these two types of features representing different semantic information were fused to form the feature representation containing both the syntactic information of syntactic dependency tree and the local information, so that the sentiment polarities of aspect words were discriminated by the classifier efficiently. Three public datasets, Restaurant, Laptop, and Twitter were used for experiment. The results show that compared with the T-GCN (Type-aware Graph Convolutional Network) model combined with the syntactic dependency tree, the proposed model has the Macro-F1 score improved by 2.48%, 2.37% and 0.32% respectively. It can be seen that the proposed model can mine potential local information effectively and predict the sentiment polarities of aspect words more accurately.

Key words: graph neural network, attention mechanism, Aspect-Based Sentiment Analysis (ABSA), local feature learning, Graph ATtention network (GAT), gated mechanism

中图分类号: