计算机科学 ›› 2023, Vol. 50 ›› Issue (10): 80-87.doi: 10.11896/jsjkx.230600036
邓入菡1,2,3, 张清华2,3, 黄帅帅1,2,3, 高满1,2,3
DENG Ruhan1,2,3, ZHANG Qinghua2,3, HUANG Shuaishuai1,2,3, GAO Man1,2,3
摘要: 方面级情感分析是情感分析中的细粒度任务,旨在检测给定句子中方面词的情感极性。随着图卷积网络的兴起,通过依赖树构建的图卷积网络模型被广泛用于该任务,并取得了令人满意的效果。但大多数研究只获取图卷积网络最后一层输出作为分类层的输入,忽略了其他层的节点特征,且深层图卷积网络存在节点平滑问题。近年来,有研究者将图卷积网络的多层节点特征进行集成,提高了情感分类模型的性能。文中结合自适应特征融合与高速公路网络,提出了一种基于多粒度特征融合的高速公路图卷积网络模型,用于方面级情感分析。首先,该模型通过句法依赖结构和双向的上下文信息构建图卷积网络;同时,在图卷积网络引入高速公路网络缓解深层图卷积网络过平滑的问题,加深图卷积网络的深度。然后,使用自适应融合机制从不同深度图卷积网络获得多粒度节点信息。最后,在公共数据集上进行实验,实验结果表明,与基准模型相比,所提模型能更好地捕获更多粒度的句法信息和长距离依存关系。
中图分类号:
[1]D'ANIELLO G,GAETA M,LA ROCCA I.KnowMIS-ABSA:An overview and a reference model for applications of sentiment analysis and aspect-based sentiment analysis[J].Artificial Intelligence Review,2022,55(7):5543-5574. [2]HOCHREITER S,SCHMIDHUBER J.Long short-term memory[J].Neural Computation,1997,9(8):1735-1780. [3]CHEN P,SUN Z Q,BING L D,et al.Recurrent Attention Network on Memory for Aspect-basedSentiment Analysis[C]//Proceedings of the 2017 Conference on Empirical Methods in Natural Language Processing(EMNLP).Stroudsburg,PA:ACL,2017:452-461. [4]YANN L,LÉON B,YOSHUA B,et al.Gradient-based learning applied to document recognition[J].Proceedings of the IEEE,1998,86(11):2278-2324. [5]VASWANI A,SHAZEER N,PARMAR N,et al.Attention Is All You Need[C]//Proceedings of the 31st International Conference on Neural Information Processing Systems.Red Hook,NY:NIPS,2017:6000-6010. [6]TANGD Y,QIN B,LIU T.Aspect Level Sentiment Classification with Deep Memory Network[C]//Proceedings of the 2016 Conference on Empirical Methods in Natural Language Proces-sing(EMNLP).Stroudsburg,PA:ACL,2016:214-224. [7]HUANG B X,OU Y,CARLEY K M.Aspect Level SentimentClassification with Attention-over-attention Neural Networks[C]//International Conference on Social Computing,Behaviral-Cultural Modeling and Prediction and Behavior Representation in Modeling and Simulation.Berlin:Springer,2018:197-206. [8]LIANG Y,MAO C S,LUO Y.Graph Convolutional Networksfor Text Classification[C]//Proceedings of the AAAI Confe-rence on Artificial Intelligence.Menlo Park,CA:AAAI,2019:7370-7377. [9]ZHANG C,LI Q C,SONG D W.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(EMNLP-IJCNLP).Stroudsburg,PA:ACL,2019:4567-4577. [10]ZHANG M,QIAN T Y.Convolution over Hierarchical Syntactic and Lexical Graphs for Aspect Level Sentiment Analysis[C]//Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing.Stroudsburg,PA:ACL,2020:3540-3549. [11]KIPF T N,WELLING M.Semi-supervised Classification withGraph Convolutional Networks[J/OL].https://arxiv.org/abs/1609.02907.pdf. [12]SRIVASTAVA R K,GREFF K,SCHMIDHUBER J.HighwayNetworks[J/OL].https://arxiv.org/pdf/1505.00387.pdf. [13]LI G H,MÜLLER M,QIAN G C,et al.Deepgcns:making gcns go as deep as cnns[J].arXiv:1904.03751.2019. [14]PANG S G,YAN Z H,HUANG W H,et al.Highway-based Local Graph Convolution Network for Aspect-based Sentiment Analysis[C]//Natural Language Processing and Chinese Computing.Berlin:Springer,2021:544-556. [15]PEDRYCZ W.Granular Computing:an Introduction[C]//Pro-ceedings Joint 9th IFSA World Congress and 20th NAFIPS International Conference(Cat.No.01TH8569).Piscataway:IEEE,2001:1349-1354. [16]YAO Y Y.A triarchic theory of granular computing[J].Granular Computing,2016(1):145-157. [17]WANG G Y,HU J,ZHANG Q H,et al.Granular Computing based Data Mining in the Views of Rough Set and Fuzzy Set[C]//2008 IEEE International Conference on Granular Computing.Piscataway:IEEE,2008:67-67. [18]LIU S T,HUANG D,WANG Y H.Learning Spatial Fusion for Single-shot Object Detec-tion[C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition.Los Alamitos,CA:IEEE Computer Society,2020:4016-4025. [19]LIU S M,CHEN J H.A multi-label classification based ap-proach for sentiment classification[J].Expert Systems with Applications,2015,42(3):1083-1093. [20]MULLEN T,COLLIER N.Sentiment Analysis using SupportVector Machines with Diverse Information Sources[C]//Proceedings of the 2004 Conference on Empirical Methods in Natural Language Processing(EMNLP).Barcelona,Spain:ACL,2004:412-418. [21]TANG D Y,QIN B,FENG X C,et al.Effective Lstms for Target-dependent Sentiment Classification[C]//Proceedings of COLING 2016,the 26th International Conference on Computational Linguistics:Technical Papers.Berlin:COLING,2016:3298-3307. [22]WANG Y Q,HUANG M L,ZHU X Y,et al. Attention-based Lstm for Aspect-level Sentiment Classification[C]//Proceedings of the 2016 Conference on Empirical Methods in Natural Language Processing(EMNLP).Stroudsburg,PA:ACL,2016:606-615. [23]TAY Y,TUAN L A,HUI S C.Learning to Attend Via Word-aspect Associative Fusion for Aspect-based Sentiment Analysis[C]//Proceedings of the AAAI Conference on Artificial Intelligence.Menlo Park,CA:AAAI,2018:5956-5963. [24]HU M T,ZHAO S W,GUO H L,et al.Learning to DetectOpinion Snippet for Aspect-based Sentiment Analysis[C]//Proceedings of the 23rd Conference on Computational Natural Language Learning(CoNLL).Stroudsburg,PA:ACL,2019:970-979. [25]BECK D,HAFFARI G,COHN T.Graph-to-sequence Learning Using Gated Graph Neural Networks[C]//Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics.Stroudsburg,PA:ACL,2018:273-283. [26]SUN K,ZHANG R C,MENSAH S,et al.Aspect-level Sentiment Analysis Via Convolution over Dependency Tree[C]//Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing(EMNLP-IJCNLP).Stroudsburg,PA:ACL,2019:5679-5688. [27]ZHU X F,ZHU L,GUO J F,et al.Gl-gcn:Global and local dependency guided graph convolutional networks for aspect-based sentiment classification[J].Expert Systems with Applications,2021,186:115712. [28]HUANG B X,CARLEY K.Syntax-aware Aspect Level Senti-ment Classification with Graph Attention Networks[C]//Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International JointConfe-rence on Natural Language Processing(EMNLP-IJCNLP).Stroudsburg,PA:ACL,2019:5469-5477. [29]WANG K,SHEN W Z,YANG Y 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,PA:ACL,2020:3229-3238. [30]LIANG B,SU H,YIN R D,et al.Beta Distribution Guided Aspect-aware Graph for Aspect Category Sentiment Analysis with Affective Knowledge[C]//Proceedings of the 2021 Conference onEmpirical Methods in Natural Language Processing(EMNLP).Stroudsburg,PA:ACL,2021:208-218. [31]YU B G,ZHANG S W.A novel weight-oriented graph convolutional network for aspect-based sentiment analysis[J].The Journal of Supercomputing,2023,79(1):947-972. [32]TIAN Y H,CHEN G M,SONG Y.Aspect-based SentimentAnalysis 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:Human Language Technologies.Stroudsburg,PA:ACL,2021:2910-2922. [33]LI S,XU B,HAN Y K,et al.SS-GCN:Aspect-based Sentiment Analysis with Graph Convolutional Networks over Dependency Awareness[J].Computer Science,2023,50(3):3-11. [34]DONG L,WEI F R,TAN C Q,et al.Adaptive Recursive Neural Network for Target-dependent Twitter Sentiment Classification[C]//Proceedings of the 52nd Annual Meeting of the Association for Computational Linguistics.Stroudsburg,PA:ACL,2014:49-54. [35]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(SemEval 2014).Stroudsburg,PA:ACL,2014:27-35. [36]PONTIKI M,GALANIS D,PAPAGEORGIOU H,et al.Semeval-2015 Task 12:Aspect based Sentiment Analysis[C]//Proceedings of the 9th international workshop on semantic evaluation(SemEval 2015).Stroudsburg,PA:ACL,2015:486-495. [37]PONTIKI M,GALANIS D,PAPAGEORGIOU H,et al.Sem-Eval-2016 Task 5:Aspect based Sentiment Analysis[C]//Proceedings of the 10th International Workshop on Semantic Eva-luation(SemEVal-2016).Stroudsburg,PA:ACL,2016:9-30. [38]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(EMNLP).Stroudsburg,PA:ACL,2014:1532-1543. [39]LI X,BING L D,LAM W,et al.Transformation Networks for Target-oriented Sentiment Classification[C]//Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics.Stroudsburg,PA:ACL,2018:946-956. [40]WANG X,LIU P,ZHU Z,et al.Aspect-based Sentiment Analysis with Graph Convolutional Networks over Dependency Awareness[C]//2022 26th International Conference on Pattern Recognition.Piscataway:IEEE,2022:2238-2245. |
|