计算机科学

计算机科学 ›› 2024, Vol. 51 ›› Issue (3): 205-213.doi: 10.11896/jsjkx.230100035

• 人工智能 • 上一篇    下一篇

基于依赖类型剪枝的双特征自适应融合网络用于方面级情感分析

郑诚1,2, 石景伟1,2, 魏素华1,2, 程嘉铭1   

  1. 1 安徽大学计算机科学与技术学院 合肥230601
    2 计算智能与信号处理教育部重点实验室(安徽大学) 合肥230601
  • 收稿日期:2023-01-06 修回日期:2023-07-13 出版日期:2024-03-15 发布日期:2024-03-13
  • 通讯作者: 郑诚(csahu@126.com)
  • 基金资助:
    安徽省重点研究与开发计划(202004d07020009)

Dual Feature Adaptive Fusion Network Based on Dependency Type Pruning for Aspect-basedSentiment Analysis

ZHENG Cheng1,2, SHI Jingwei1,2, WEI Suhua1,2, CHENG Jiaming1   

  1. 1 School of Computer Science and Technology,Anhui University,Hefei 230601,China
    2 Key Laboratory of Intelligent Computing & Signal Processing(Anhui University),Ministry of Education,Hefei 230601,China
  • Received:2023-01-06 Revised:2023-07-13 Online:2024-03-15 Published:2024-03-13
  • About author:ZHENG Cheng,born in 1964,Ph.D,associate professor.His main research interests include data mining and text analysis,and natural language proces-sing.
  • Supported by:
    Key Research and Development Project of Anhui Province(202004d07020009).

PDF (PC)

127

摘要： 现有的模型将基于依赖树的图神经网络用于方面级情感分析,一定程度上提升了模型的分类性能。然而,由于依赖解析技术的限制,语法解析结果的不精确导致依赖树存在大量噪声,使得模型的性能提升有限。此外,一些句子本身并不符合标准的句法结构。以往的研究以同样的置信度利用句法信息和语义信息,没有充分考虑它们对于确定方面词极性的贡献的不同,导致模型在相应的数据集上性能较差。为了克服这些困难,文中提出了一种基于依赖类型剪枝的双特征自适应融合网络。具体来说,该模型使用一种新型的混合方法,命名为依赖关系类型剪枝和邻接矩阵平滑,来缓解句法解析产生的噪声。此外,该模型通过双特征自适应融合模块充分考虑句子的句法信息的可用程度,以一种更灵活的方式将句法特征和语义特征结合起来用于方面级情感分析。在5个公开可用的数据集上进行广泛的实验,结果证明了该方法明显优于基线模型。

关键词: 方面级情感分析, 图神经网络, 依赖类型剪枝, 双特征自适应融合, 深度学习, 自然语言处理

Abstract: Existing models use graph neural network based on dependency trees for aspect-based sentiment analysis,which improves the classification performanceof the model to a certain extent.However,due to technical limitations of dependency parsing,the inaccuracy of the dependency parsing results leads to a large amount of noise in the dependency tree,which makes the performance improvement of the model is limited.In addition,some sentences themselves do not conform to the standard syntactic structure.Previous studies utilized syntactic and semantic information with the same confidence level without fully considering the difference in their contributions to determining the polarity of aspect words,resulting in poor model performance on the corres-ponding datasets.To overcome these challenges,a dual feature adaptive fusion network based on dependency type pruning is proposed in this paper.Specifically,the model uses a novel hybrid approach,named dependency type pruning and adjacency matrix smoothing,to mitigate the noise generated by dependency parsing.In addition,the model fully considers the availability of syntactic information of sentences through a dual feature adaptive fusion module to combine syntactic features and semantic features for aspect-level sentiment analysis in a more flexible way.Extensive experiments on five publicly available datasets demonstrate that the proposed method significantly outperforms baseline models.

Key words: Aspect-based sentiment analysis, Graph neural networks, Dependency type pruning, Dual feature adaptive fusion, Deep learning, Natural language processing

中图分类号: 

  • TP391
[1]LIU J,TENG Z,CUI L,et al.Solving Aspect Category Senti-ment Analysis as a Text Generation Task[C]//Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing.Stroudsburg:ACL,2021:4406-4416.
[2]LIN Y,FU Y,LI Y,et al.Aspect-based sentiment analysis for online reviews with hybrid attention networks[J].World Wide Web,2021,24(4):1215-1233.
[3]LI Y,WANG C,LIN Y,et al.Span-based relational graph transformer network for aspect-opinion pair extraction[J].Knowledge and Information Systems,2022,64(5):1305-1322.
[4]GAO L,WANG Y,LIU T,et al.Question-driven span labeling model for aspect-opinion pair extraction[C]//Proceedings of the AAAI Conference on Artificial Intelligence.Palo Alto:AAAI Press,2021:12875-12883.
[5]WU S,FEI H,REN Y,et al.Learn from Syntax:Improving Pair-wise Aspect and Opinion Terms Extraction with Rich Syntactic Knowledge[C]//Proceedings of the Thirtieth Interna-tional Joint Conference on Artificial Intelligence.San Francisco:Morgan Kaufmann,2021:3957-3963.
[6]LI Y,LIN Y,LIN Y,et al.A span-sharing joint extractionframework for harvesting aspect sentiment triples[J].Know-ledge-Based Systems,2022,242(2):108366.
[7]LIU Y,LIU Q,DAI D,et al.Unified Structure Generation forUniversal Information Extraction[C]//Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics.Stroudsburg:ACL,2022:5755-5772.
[8]MAO Y,SHEN Y,YANG J,et al.Seq2path:Generating sentiment tuples as paths of a tree[C]//Findings of the Association for Computational Linguistics.Stroudsburg:ACL,2022:2215-2225.
[9]BAO X,WANG Z,JIANG X,et al.Aspect-based SentimentAnalysis with Opinion Tree Generation[C]//Proceedings of the Thirty-First International Joint Conference on Artificial Intelligence.San Francisco:Morgan Kaufmann,2022:4044-4050.
[10]ZHANG C,LI Q,SONG D.Syntax-aware aspect-level sentiment classification with proximity-weighted convolution network[C]//Proceedings of the 42nd International ACM SIGIR Confe-rence on Research and De-velopment in Information Retrieval.New York:ACM,2019:1145-1148.
[11]ZHANG C,LI Q,SONG D.Aspect-based Sentiment Classification with Aspect-specific Graph Convolutional Networks[C]//Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing.Stroudsburg:ACL,2019:4567-4577.
[12]WANG K,SHEN W,YANG Y,et al.Relational Graph Attention Network for Aspect-based Sentiment Analysis[C]//Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics.Stroudsburg:ACL,2020:3229-3238.
[13]CHEN J,HUANG Z,XUE Y.Bilateral-brain-like Semantic and Syntactic Cognitive Network for Aspect-level Sentiment Analysis[C]//2021 International Joint Conference on Neural Networks.Piscataway:IEEE,2021:1-8.
[14]PANG B,LEE L.Opinion Mining and Sentiment Analysis[J].Applied and Environmental Microbiology,2008,2(1/2):1-135.
[15]KIRITCHENKO S,ZHU X,CHERRY C,et al.NRC-Canada-2014:Detecting Aspects and Sentiment in Customer Reviews[C]//Proceedings of the 8th International Workshop on Semantic Evaluation.Stroudsburg:ACL,2014:437-442.
[16]MARCHEGGIANI D,TÄCKSTRÖM O,ESULI A,et al.Hie-rarchical multi-label conditional random fields for aspect-oriented opinion mining[C]//European Conference on Information Retrieval.Cham:Springer,2014:273-285.
[17]MNIH V,HEESS N,GRAVES A.Recurrent Models of Visual Attention[J].Advances in Neural Information Processing Systems,2014,27(2):2204-2212.
[18]WANG Y,HUANG M,ZHU X,et al.Attention-based LSTMfor Aspect-level Sentiment Classification[C]//Proceedings of the 2016 Conference on Empirical Methods in Natural Language Processing.Stroudsburg:ACL,2016:606-615.
[19]LIU J,ZHANG Y.Attention modeling for targeted sentiment[C]//Proceedings of the 15th Conference of the European Chapter of the Association for Computational Linguistics.Stroudsburg:ACL,2017:572-577.
[20]FAN F,FENG Y,ZHAO D.Multi-grained attention network for aspect-level sentiment classification[C]//Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing.Stroudsburg:ACL,2018:3433-3442.
[21]BAO L,LAMBERT P,BADIA T.Attention and Lexicon Regularized LSTM for Aspect-based Sentiment Analysis[C]//Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics.Stroudsburg:ACL,2019:253-259.
[22]HE R,LEE W,NG H,et al.Effective Attention Modeling forAspect-Level Sentiment Classification[C]//Proceedings of the 27th International Conference on Computational Linguistics.Stroudsburg:ACL,2018:1121-1131.
[23]SUN K,ZHANG R,MENSAH S,et al.Aspect-Level Sentiment Analysis Via Convolution over Dependency Tree[C]//Procee-dings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing.Stroudsburg:ACL,2019:5678-5687.
[24]HUANG B,CARLEY K M.Syntax-Aware Aspect Level Sentiment Classification with Graph Attention Networks[C]//Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Confe-rence on Natural Language Processing.Stroudsburg:ACL,2019:5468-5476.
[25]TIAN Y,CHEN G,SONG Y.Aspect-based Sentiment Analysis with Type-aware Graph Convolutional Networks and Layer Ensemble[C]//Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics.Stroudsburg:ACL,2021:2910-2922.
[26]HOU X,QI P,WANG G,et al.Graph Ensemble Learning over Multiple Dependency Trees for Aspect-level Sentiment Classification [C]//Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics.Washington:NAACL,2021:2884-2894.
[27]LI R,CHEN H,FENG F,et al.Dual Graph Convolutional Networks 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.Stroudsburg:ACL,2021:6319-6329.
[28]PENNINGTON J,SOCHER R,MANNING C D.Glove:Global Vectors for Word Representation[C]//Proceedings of the 2014 Conference on Empirical Methods in Natural Language Proces-sing.Stroudsburg:ACL,2014:1532-1543.
[29]KOTA V R,MUNISAMY S D.High accuracy offering attention mechanisms based deep learning approach using CNN/bi-LSTM for sentiment analysis[J].International Journal of Intelligent Computing and Cybernetics,2022,15(1):61-74.
[30]LIANG S,WEI W,MAO X L,et al.BiSyn-GAT+:Bi-SyntaxAware Graph Attention Network for Aspect-based Sentiment Analysis[C]//Findings of the Association for Computational Linguistics:ACL 2022.Stroudsburg:ACL,2022:1835-1848.
[31]LIU B,BEN A,GALDRAN A,et al.The Devil is in the Margin:Margin-based Label Smoothing for Network Calibration[C]//Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition.Piscataway:IEEE,2022:80-88.
[32]LI Q,HAN Z,WU X,et al.Deeper Insights Into Graph Convolutional Networks for Semi-Supervised Learning[C]//Procee-dings of the Thirty-Second AAAI Conference on Artificial Intelligence.Palo Alto:AAAI Press,2018:3538-3545.
[33]PONTIKI M,GALANIS D,PAVLOPOULOS J,et al.SemEval-2014 Task 4:Aspect Based Sentiment Analysis[C]//Procee-dings of the 8th International Workshop on Semantic Evaluation.Stroudsburg:ACL,2014:27-35.
[34]PONTIKI M,GALANIS D,PAPAGEORGOU H,et al.Semeval-2015 task 12:Aspect based sentiment analysis[C]//Proceedings of the 9th International Workshop on Semantic Evaluation.Stroudsburg:ACL,2015:486-495.
[35]PONTIKI M,GALANIS D,PAPAGEORGOU H,et al.Semeval-2016 task 5:Aspect based sentiment analysis[C]//Proceedings of the 10th International Workshop on Semantic Evaluation.Stroudsburg:ACL,2016:19-30.
[36]DONG L,WEI F,TAN C,et al.Adaptive Recursive Neural Network for Targetde-pendent Twitter Sentiment Classification[C]//Proceedings of the 52nd Annual Meeting of the Association for Computational Linguistics.Stroudsburg:ACL,2014:49-54.
[37]MA D,LI S,ZHANG X,et al.Interactive Attention Networks for Aspect-Level Sentiment Classification[C]//Proceedings of the Twenty-Sixth International Joint Conference on Artificial Intelligence.San Francisco:Morgan Kaufmann,2017:4068-4074.
[38]HUANG B,OU Y,CARLEY K M.Aspect Level SentimentClassification with Attention-over-Attention Neural Networks[C]//International Conference on Social Computing,Behavioral-cultural Modeling and Prediction and Behavior Representation in Modeling and Simulation.Cham:Springer,2018:197-206.
[39]ZHANG M,QIAN T.Convolution over Hierarchical Syntacticand Lexical Graphs for Aspect Level Sentiment Analysis[C]//Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing.Association for Computational Linguistics.Stroudsburg:ACL,2020:3540-3549.
[40]BURSTEIN J,DORAN C,SOLORIO T,et al.BERT:Pre-trai-ning of Deep Bidirectional Transformers for Language Understanding [C]//Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics.Stroudsburg:ACL,2019:4171-4186.
Viewed
Full text


Abstract

Cited
  Shared   
  Discussed   
No Suggested Reading articles found!
渝ICP备16013121号-4
地址：重庆市渝北区洪湖西路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