该文针对前人研究中依存语法的学习建模过程与文本情感特征提取模块完全独立的问题,考虑到很难根据新数据进行整体更新,结合引入自然实体知识至神经网络的新方式,为问答式情感分析任务提出了结合自然语言知识和图卷积网络的双重网络模型E-QAGCN。模型考虑了词语间的相互依赖关系,并基于依存语法树的结构特征,将依赖句法关系融入语义向量表示中,联合自然语言知识和多层图卷积网络模型对文本进行了深层次的情感特征提取。此为基于依存语法树和图卷积操作结构的方法第一次在问答式情感分析任务中被应用,在三个领域的中文问答式情感分析数据集上的实验结果验证了该模型的有效性,达到了同期的最优效果。
Abstract
To deal with the issue that dependency grammar learning process and text sentiment feature extraction is independent, considering the difficulty in making overall updates based on new data. This paper put forward a dual network model E-QAGCN to introduce the natural entity knowledge into the neural network. Based on the structural features of text dependency tree, the model takes into account the inter-relationship between words, and combines the knowledge of natural language to extract the deep sentiment features of the text through multi-layer graph convolution network. This is the first time that the dependency tree-based sentiment feature extraction from text via GCN has been applied in question-answering Sentiment Analysis task. The experimental results on three Chinese datasets prove the effectiveness of the model by achieving the best result.
关键词
图神经网络 /
情感分析 /
实体知识
{{custom_keyword}} /
Key words
graph neural network /
sentiment analysis /
entity knowledge
{{custom_keyword}} /
{{custom_sec.title}}
{{custom_sec.title}}
{{custom_sec.content}}
参考文献
[1] HU G, SHI C, HAO S, et al. Residual-duet network with tree dependency representation for Chinese question-answering sentiment analysis[C/OL]//Proceedings of the 43rd International ACM SIGIR Conference on Research and Development in Information Retrieval. Virtual Event, China: SIGIR, 2020: 1725-1728.
[2] WILSON T, WIEBE J, HOFFMANN P. Recognizing contextual polarity in phrase-level sentiment analysis[C]//Proceedings of Human Language Technology Conference and Conference on Empirical Methods in Natural Language Processing. Vancouver, British Columbia, Canada: HLT/EMNLP, 2005: 347-354.
[3] LI S, HUANG C, ZHOU G, et al. Employing personal/impersonal views in supervised and semisupervised sentiment classification[C]//Proceedings of the 48th Annual Meeting of the Association for Computational Linguistics. Uppsala, Sweden: ACL, 2010: 414-423.
[4] KIM Y. Convolutional neural networks for sentenceclassification[C]//Proceedings of the Conference on Empirical Methods in Natural Language Processing. Doha, Qatar: EMNLP, 2014: 1746-1751.
[5] WANG H, LIU B, LI C, et al.Learning with noisy labels for sentence-level sentiment classification[C]//Proceedings of the Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing. Hong Kong, China: EMNLP/IJCNLP, 2019: 6285-6291.
[6] MA Y, PENG H, CAMBRIA E. Targeted aspect-based sentiment analysis via embedding commonsense knowledge into an attentive LSTM[C]//Proceedings of the 32nd AAAI Conference on Artificial Intelligence. New Orleans, Louisiana, USA: AAAI, 2018:5876-5883.
[7] WU Z, DAI X, YIN C, et al. Improving review representations with user attention and product attention for sentiment classification[C]//Proceedings of the 32nd AAAI Conference on Artificial Intelligence. New Orleans, Louisiana, USA: AAAI, 2018: 5989-5996.
[8] WANG Y, HUANG M, ZHU X, et al. Attention-based LSTM for aspect-level sentiment classification[C]//Proceedings of the Conference on Empirical Methods in Natural Language Processing. Austin, Texas, USA: EMNLP, 2016: 606-615.
[9] SUN C, HUANG L, QIU X. Utilizing BERT for aspect-based sentiment analysis via constructing auxiliary sentence[C]//Proceedings of the Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies Minneapolis. MN, USA: ACL, 2019, 380-385.
[10] TIAN H, GAO C, XIAO X, et al. SKEP: Sentiment knowledge enhanced pre-training for sentiment analysis[C]//Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics. Online: ACL, 2020: 4067-4076.
[11] SHEN C, SUN C, WANG J, et al. Sentiment classification towards question-answering with hierarchical matching network[C]//Proceedings of the Conference on Empirical Methods in Natural Language Processing. Brussels, Belgium: EMNLP, 2018: 3654-3663.
[12] WANG J, SUN C, LI S, et al. Aspect sentiment classification towards question-answering with reinforced bidirectional attention network[C]//Proceedings of the 57th Conference of the Association for Computational Linguistics. Florence, Italy: ACL, 2019, 3548-3557.
[13] LI S, ZHAO Z, HU R, et al. Analogical reasoning on chinese morphological and semantic relations[C]//Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics. Melbourne, Australia: ACL, 2018: 138-143.
[14] VASWANI A, SHAZEER N, PARMAR N, et al. Attention is all you need[C]//Proceedings of Advances in Neural Information Processing Systems 30: Annual Conference on Neural Information Processing Systems. Long Beach, CA, USA: NIPS, 2017: 5998-6008.
[15] JOHNSON R, ZHANG T. Deep pyramid convolutional neural networks for text categorization[C]//Proceedings of the 55th Annual Meeting of the Association for Computational Linguistics. Vancouver, Canada: ACL, 2017, 562-570.
[16] YAO L, MAO C, LUO Y. Graph convolutional networks for text classification[C]//Proceedings of the 33rd AAAI Conference on Artificial Intelligence. Honolulu, Hawaii, USA: AAAI, 2019: 7370-7377.
[17] SUN K, ZHANG R, MENSAH S, et al. Aspect-level sentiment analysis via convolution over dependency tree[C]//Proceedings of the Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing. Hong Kong, China: EMNLP,2019: 5678-5687.
[18] SUN Y, WANG S, LI Y, et al. ERNIE: Enhanced Representation through Knowledge Integration[J/OL]. CoRR, abs/1904.09223, 2019.
[19] ZHANG Y, YU X, CUI Z, et al. Every document owns its structure: Inductive text classification via graph neural networks[C]//Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics. Online: ACL, 2020: 334-339.
[20] BAI X, LIU P, ZHANG Y. Investigating typed syntactic dependencies for targeted sentiment classification using graph attention neural network[J]. IEEE ACM Trans. Audio Speech Lang. Process, 2021, 29: 503-514.
{{custom_fnGroup.title_cn}}
脚注
{{custom_fn.content}}
基金
国家重点研究与发展计划(2019YFB1406300)
{{custom_fund}}
PDF(3474 KB)
