方面级情感分析是细粒度情感分析的一个基本子任务,旨在预测文本中给定方面或实体的情感极性。语义信息、句法信息及其交互信息对于方面级情感分析是极其重要的。该文提出一种基于图卷积和注意力的网络模型(CA-GCN)。该模型主要分为两部分,一是将卷积神经网络结合双向LSTM获取的丰富特征表示与图卷积神经网络掩码得到的方面特征表示进行融合;二是采用两个多头交互注意力融合方面、上下文和经图卷积神经网络得到的特征信息,而后接入多头自注意力来学习信息交互后句子内部的词依赖关系。与ASGCN模型相比,该模型在三个基准数据集(Twitter、Lap14和Rest14)上准确率分别提升1.06%、1.62%和0.95%,F1值分别提升1.07%、2.60%和1.98%。
Abstract
Aspect-level sentiment analysis is a fundamental subtask of fine-grained sentiment analysis to predict the sentiment polarities of the given aspects or entities in text. The semantic information, syntactic information and their internteractive information are crucial to aspect-level sentiment analysis. This paper proposes a CA-GCN model based on graph convolution and attention. The model is mainly divided into two parts. First, the model integrates the rich feature representation obtained by CNN and Bi-LSTM with the aspect-oriented features obtained through graph convolution. Second ,the model applied two multi-head interactive attention to integrate the aspect, the context and the feature information obtained by the graph convolution, which is then fed into a multi-head self-attention to learn the dependency relationship among words in the sentence. Compared with the ASGCN model, the accuracy of the model on the datasets of Twitter,Lap14 and Rest14 is improved by 1.06%,1.62% and 0.95%, and the F1 score is improves by 1.07%,2.60% and 1.98%,respectively.
关键词
特定方面情感分析 /
图卷积网络 /
注意力机制
{{custom_keyword}} /
Key words
aspect-level sentiment analysis /
graph convolutional network (GCN) /
attention mechanism
{{custom_keyword}} /
{{custom_sec.title}}
{{custom_sec.title}}
{{custom_sec.content}}
参考文献
[1] Zhang M S, Zhang Y, Vo D T. Gated neural networks for targeted sentiment analysis[C]//Proceedings of the 30th AAAI Conference on Artificial Intelligence, 2016: 3087-3083.
[2] Jiang L, Yu M, Zhou M, et al. Target-dependent twitter sentiment classification[C]//Proceedings of the 49th Annual Meeting of the Association for Computational Linguistics, 2011: 151-160.
[3] Xue W,Li T. Aspect based sentiment analysis with gated convolutional networks[C]//Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics, 2018: 2514-2523.
[4] 刘全,梁斌,徐进,等.一种用于基于方面情感分析的深度分层网络模型[J]. 计算机学报, 2018, 41 (12): 2637-2652.
[5] 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, 2016: 606-615.
[6] Ma D, Li S, Zhang X, et al. Interactive attention networks for aspect-level sentiment classification[C]//Proceedings of the 26th International Joint Conference on Artificial Intelligence, 2017: 4068-4074.
[7] Li X, Bing L, Lam W, et al. Transformation networks for target-oriented sentiment classification[C]//Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics, 2018: 946-956.
[8] Li X, Song J, Gao L, et al. Beyond rnns: Positional self-attention with co-attention for video question answering[C]//Proceedings of the AAAI Conference on Artificial Intelligence, 2019: 8658-8665.
[9] Nguyen T H, Shirai K. Phrasernn: Phrase recursive neural network for aspect-based sentiment analysis[C]//Proceedings of the Conference on Empirical Methods in Natural Language Processing, 2015: 2509-2514.
[10] Rao D, Ravichandran D. Semi-supervised polarity lexicon induction[C]//Proceedings of the 12th Conference of the European Chapter of the ACL, 2009: 675-682.
[11] Dong L, Wei F, Tan C, et al. Adaptive recursive neural network for target-dependent twitter sentiment classification[C]//Proceeding of the 52nd Annual Meeting of the Association for Computational Linguistics, 2014: 49-54.
[12] Ma X, Zeng J, Peng L,et al. Modeling multi-aspects within one opinionated sentence simultaneously for aspect-level sentiment analysis[J]. Future Generation Computer Systems, 2019, 93: 304-311.
[13] Chen P, Sun Z, BingL, et al. Recurrent attention network on memoryfor aspect sentiment analysis[C]//Proceedings of the Conference on Empirical Methods in Natural Language Processing, 2017: 452-461.
[14] Fan F, Feng Y, Zhao D. Multi-grained attention network for aspect-level sentiment classification[C]//Proceedings of the Conference on Empirical Methods in Natural Language Processing, 2018: 3433-3442.
[15] Bruna J, Zaremba W, Szlam A,et al. Spectral networks and locally connected networkson graphs[J]. arXiv preprint arXiv: 1312.6203, 2013.
[16] Li Y, Ouyang W, Zhou B, et al. Factorizable net: An efficient subgraph-based framework for scene graph generation[C]//Proceedings of the European Conference on Computer Vision, 2018: 335-351.
[17] Marcheggiani D, Titov I. Encoding sentences with graph convolutional networks for semantic role labeling[J]. arXiv preprint arXiv: 1703.04826, 2017.
[18] Bastings J, Titov I, Aziz W, et al. Graph convolutional encoders for syntax-aware neural machine translation[J]. arXiv preprint arXiv: 1704.04675,2017.
[19] Li Y, Jin R, Luo Y. Classifying relations in clinical narratives using segment graph convolutional and recurrent neural networks[J]. Journal of the American Medical Informatics Association, 2019, 26(3): 262-268.
[20] Peng H, Li J, He Y, et al. Large-scale hierarchical text classification with recursively regularized deep graph-cnn[C]//Proceedings of the World Wide Web Conference, 2018: 1063-1072.
[21] Zhang Y, Liu Q, Song L. Sentence-state lstm for text representation[C]//Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics, 2018: 317-327.
[22] Kipf T, Welling M. Semi-supervised classification with graph convolutional networks[C]//Proceedings of the 5th International Conference on Learning Representations, 2016.
[23] Zhang C, Li Q, Song D. Aspect-based sentiment classification with aspect-specific graph convolutional networks[C]//Proceedings of the Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing, 2019: 4560-4570.
[24] 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, 2019: 5683-5692.
[25] Tang D, Qin B, Feng X, et al. Effective LSTMs for target-dependent sentiment classification[C]//Proceedings of the 26th International Conference on Computational Linguistics, 2016: 3298-3307.
[26] Song Y, Wang J, Jiang T, et al. Attentional encoder network for targeted sentiment classification[J].arXiv preprint arXiv: 1902.09314, 2019.
[27] Jiang L, Yu M, Zhou M, et al. Target-dependent twitter sentiment classification[C]//Proceedings of the 49th Annual Meeting of the Association for Computational Linguistics: Human Language Technologies, 2011: 151-160.
{{custom_fnGroup.title_cn}}
脚注
{{custom_fn.content}}
PDF(2693 KB)
