目前方面级情感分析方法主要利用注意力机制来实现句子与方面词的交互,然而该机制容易导致方面词与句子中各词的错误搭配,引入额外噪声。针对此问题,该文提出了一种基于特征双重蒸馏网络的方面级情感分析方法。首先利用BiLSTM提取句子中各词的上下文语义特征,并结合基于上下文的方面词嵌入方法,获取方面词的语义特征。进一步地,利用门控机制构建双重蒸馏门,通过初步蒸馏与精细蒸馏两个过程实现句子与方面词的语义特征交互,获取与方面词相关的句子情感语义特征。最终利用Softmax对获取的情感语义特征进行情感分类。在通用的Laptop、Restaurant和Twitter数据集上进行实验,结果表明,该方法的准确率分别达到79.26%、84.53%和75.30%,宏平均F1值分别达到75.77%、75.63%和73.21%,优于目前主流方法。
Abstract
Current methods of aspect-based sentiment analysis usually utilize the attention mechanism to fulfill the interaction between sentence and aspect. However, the attention mechanism often results in the mismatches between words of sentence and aspect, which will introduce extraneous noise. To address this issue, this paper proposes a feature dual distillation network for aspect-based sentiment analysis. Firstly, BiLSTM is utilized to extract context semantic features, and a context-based aspect embedding is utilized to obtain the semantic feature of aspect. Moreover, a gate mechanism is employed to construct a dual distillation gate where preliminary distillation and fine distillation processes are utilized to fulfill the interaction between the semantic features of sentence and aspect. Finally, Softmax is utilized to predict the sentiment polarities. On commonly used Laptop, Restaurant and Twitter datasets, the proposed method performs better than the state-of-the-art methods with 79.26%, 84.53% and 75.30% accuracy, and 75.77%, 75.63% and 73.21% Macro-F1, respectively.
关键词
方面级情感分析 /
门控机制 /
双重蒸馏 /
神经网络
{{custom_keyword}} /
Key words
aspect-based sentiment analysis /
gate mechanism /
dual distillation /
neural network
{{custom_keyword}} /
{{custom_sec.title}}
{{custom_sec.title}}
{{custom_sec.content}}
参考文献
[1] 贾川, 方睿, 浦东,等. 基于循环实体网络的细粒度情感分析[J]. 中文信息学报, 2019, 33(9): 123-128.
[2] Khaidem L, Saha S, Dey S R. Predicting the direction of stock market prices using random forest[J]. arXiv preprint arXiv:160500003, 2016.
[3] Tumasjan A, Sprenger T O, Sandner P G, et al. Predicting elections with twitter: What 140 characters reveal about political sentiment[C]//Proceedings of the 4th International AAAI Conference on Weblogs and Social Media, 2010: 1279-1282
[4] Cambria E, Hussain A, Durrani T, et al. Sentic computing for patient centered applications[C]//Proceedings of the 10th IEEE International Conference on Signal Processing Proceedings, 2010: 1279-1282.
[5] Zhang Z, Liu Y, Xu G, et al. A weighted adaptation method on learning user preference profile[J]. Knowledge-Based Systems, 2016, 112: 114-126.
[6] Yang C, Zhang H, Jiang B, et al. Aspect-based sentiment analysis with alternating coattention networks[J]. Information Processing and Management, 2019, 56(3): 463-478.
[7] 曾锋, 曾碧卿, 韩旭丽,等. 基于双层注意力循环神经网络的方面级情感分析[J]. 中文信息学报, 2019, 33(6): 108-15.
[8] 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, 12: 2637-2652.
[9] Shuang K, Zhang Z, Guo H, et al. A sentiment information collector-extractor architecture based neural network for sentiment analysis[J]. Information Sciences, 2018, 467: 549-558.
[10] Wang L, Niu J, Yu S. SentiDiff: Combining textual information and sentiment diffusion patterns for Twitter sentiment analysis[C]//Proceedings of IEEE Transactions on Knowledge and Data Engineering, 2019.
[11] Serrano-Guerrero J, Olivas J A, Romero F P, et al. Sentiment analysis: A review and comparative analysis of web services[J]. Information Sciences, 2015, 311: 18-38.
[12] Bahdanau D, Cho K, Bengio Y. Neural machine translation by jointly learning to align and translate[J]. arXiv preprint arXiv:14090473, 2014.
[13] Song M, Park H, Shin K -s. Attention-based long short-term memory network using sentiment lexicon embedding for aspect-level sentiment analysis in Korean[J]. Information Processing and Management, 2019, 56(3): 637-653.
[14] Chen P, Sun Z, Bing L, et al. Recurrent attention network on memory for aspect sentiment analysis[C]//Proceedings of the 2017 Conference on Empirical Methods in Natural Language Processing, 2017: 452-461.
[15] Song Y, Wang J, Jiang T, et al. Attentional encoder network for targeted sentiment classification[J]. arXiv preprint arXiv:190209314, 2019.
[16] 王盛玉, 曾碧卿, 商齐,等. 基于词注意力卷积神经网络模型的情感分析研究[J]. 中文信息学报, 2018, 32(9): 123-31.
[17] Wang Y, Huang M, Zhu X, et al. Attention-based LSTM for aspect-level sentiment classification[C]//Proceedings of the 2016 Conference on Empirical Methods in Natural Language Processing, 2016: 606-615.
[18] Vo D T, Zhang Y. Target-dependent twitter sentiment classification with rich automatic features[C]//Proceedings of the 24th International Conference on Artificial Intelligence, 2015: 1347-1353.
[19] Dong L, Wei F, Tan C, 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, 2014: 49-54.
[20] 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: Technical Papers, 2016: 3298-3307.
[21] Liu N, Shen B. Aspect-based sentiment analysis with gated alternate neural network[J]. Knowledge-Based Systems, 2020, 188: 105010.
[22] 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.
[23] 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, 2017: 572-577.
[24] 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.
[25] 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 Processing (EMNLP), 2014: 1532-1543.
[26] Devlin J, Chang M W, Lee K, et al. Bert: Pre-training of deep bidirectional transformers for language understanding[J]. arXiv preprint arXiv:181004805, 2018,
[27] Pontiki M, Papageorgiou H, Galanis D, et al. SemEval-2014 Task 4: Aspect based sentiment analysis[C]//Proceedings of the SemEval 2014, 2014: 27.
[28] 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, 2014: 437-442.
[29] Tang D, Qin B, Liu T. Aspect level sentiment classification with deep memory network[C]//Proceedings of the 2016 Conference on Empirical Methods in Natural Language Processing, 2016: 214-224.
[30] Kim Y. Convolutional neural networks for sentence classification[C]//Proceedings of the 2014 Conference on Empirical Methods in Natural Language Processing, 2014: 1746-1751.
[31] Zhou J, Huang J X, Hu Q V, et al. SK-GCN: Modeling syntax and knowledge via graph convolutional network for aspect-level sentiment classification[J]. Knowledge-Based Systems, 2020, 205,106292:1-10.
[32] Liu N, Shen B. ReMemNN: A novel memory neural network for powerful interaction in aspect-based sentiment analysis[J]. Neurocomputing, 2020, 395:66-77.
{{custom_fnGroup.title_cn}}
脚注
{{custom_fn.content}}
基金
国家自然科学基金(61673193,62076110);江苏省自然科学基金(BK20181341);中国博士后科学基金(2017M621625)
{{custom_fund}}
PDF(2084 KB)
