对话情感分析旨在识别出一段对话中每个句子的情感倾向,其在电商客服数据分析中发挥着关键作用。不同于对单个句子的情感分析,对话中句子的情感倾向依赖于其在对话中的上下文。目前已有的方法主要采用循环神经网络和注意力机制建模句子之间的关系,但是忽略了对话作为一个整体所呈现的特点。建立在多任务学习的框架下,该文提出了一个新颖的方法,同时推测一段对话的主题分布和每个句子的情感倾向。对话的主题分布,作为一种全局信息,被嵌入到每个词以及句子的表示中。通过这种方法,每个词和句子被赋予了在特定对话主题下的含义。在电商客服对话数据上的实验结果表明,该文提出的模型能充分利用对话主题信息,与不考虑主题信息的基线模型相比,Macro-F1值均有明显提升。
Abstract
Dialog sentiment analysis aims to classify the sentiment polarity of each utterance in dialogue, which plays a critical role in e-commerce customer service data analysis. Unlike sentiment analysis for a single sentence, an utterance’s sentiment polarity in dialog depends on its context. The recent methods mainly focused on modeling contextual connections using recurrent neural network and attention mechanism, ignoring the characteristic of the dialogue as a whole. Choosing the multi-task learning framework, we propose a novel model of detecting dialog topic distribution and each utterance’s sentiment polarity simultaneously. Dialog topic distribution, as a kind global information, is integrated into each word/utterance representation. In this way, each word and utterance has its meaning under particular dialog topics. The experimental results on a real-world dialog dataset in e-commerce customer service show that the proposed model can make full use of the dialog topic information, and significantly outperforms the baseline model that does not consider the dialog topic in Macro-F1 score.
关键词
对话 /
情感分析 /
主题模型
{{custom_keyword}} /
Key words
dialogue /
sentiment analysis /
topic model
{{custom_keyword}} /
{{custom_sec.title}}
{{custom_sec.title}}
{{custom_sec.content}}
参考文献
[1] Mikolov T, Karafiát M, Burget L, et al. Recurrent neural network based language model[C]//Proceedings of 11th Annual Conference of the International Speech Communication Association, 2010: 1045-1048.
[2] Bahdanau D, Cho K, Bengio Y. Neural machine translation by jointly learning to align and translate[J]. arXiv preprint arXiv: 1409.0473, 2014.
[3] Kingma D P, Welling M. Auto-encoding variationalbayes[J]. arXiv preprint arXiv: 1312.6114, 2013.
[4] Miao Y, Yu L, Blunsom P. Neural variational inference for text processing[C]//Proceedings of International Conference on Machine Learning, 2016: 1727-1736.
[5] Goodfellow I, Bengio Y, Courville A. Deep learning[M]. MIT Press, 2016: 164-168.
[6] Chang C C, Lin C J. LIBSVM: A library for support vector machines[J]. ACM Transactions on Intelligent Systems and Technology (TIST), 2011, 2(3): 27.
[7] Kim Y. Convolutional neural networks for sentence classification[C]//Proceedings of the 2014 Conference on Empirical Methods in Natural Language Processing (EMNLP), 2014: 1746-1751.
[8] Hsu C C, Chen S Y, Kuo C C, et al. EmotionLines: An emotion corpus of multi-party conversations[C]//Proceedings of the 11th International Conference on Language Resources and Evaluation (LREC-2018), 2018.
[9] Cerisara C, Jafaritazehjani S, Oluokun A, et al. Multi-task dialog act and sentiment recognition on Mastodon[C]//Proceedings of the 27th International Conference on Computational Linguistics, 2018: 745-754.
[10] Sukhbaatar S, Weston J, Fergus R.End-to-end memory networks[C]//Proceedings of Advances in Neural Information Processing Systems, 2015: 2440-2448.
[11] Hazarika D, Poria S, Mihalcea R, et al. ICON: Interactive Conversational Memory Network for Multimodal Emotion Detection[C]//Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing, 2018: 2594-2604.
[12] Majumder N, Poria S, Hazarika D, et al. Dialoguernn: An attentive RNN for emotion detection in conversations[J]. arXiv preprint arXiv: 1811.00405, 2018.
[13] Hofmann T. Probabilistic latent semantic analysis[C]//Proceedings of the 15th Conference on Uncertainty in Artificial Intelligence. Morgan Kaufmann Publishers Inc., 1999: 289-296.
[14] Blei D M, Ng A Y, Jordan M I. Latent Dirichlet allocation[J]. Journal of Machine Learning Research, 2003, 3(Jan): 993-1022.
[15] Lin C, He Y. Joint sentiment/topic model for sentiment analysis[C]//Proceedings of the 18th ACM Conference on Information and Knowledge Management. ACM, 2009: 375-384.
[16] Xiang B, Zhou L. Improving twitter sentiment analysis with topic-based mixture modeling and semi-supervised training[C]//Proceedings of the 52nd Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers), 2014(2): 434-439.
[17] Ren Y, Zhang Y, Zhang M, et al. Improving twitter sentiment classification using topic-enriched multi-prototype word embeddings[C]//Proceedings of 13th AAAI Conference on Artificial Intelligence. 2016.
[18] Hochreiter S, Schmidhuber J. Long short-term memory[J]. Neural Computation, 1997, 9(8): 1735-1780.
[19] Pennington J, Socher R, Manning C. Glove: Global vectors for word representation[C]//Proceedings of the 2014 Conference on Empirical Methods in Natural Language Processing (EMNLP), 2014: 1532-1543.
[20] Glorot X, Bengio Y. Understanding the difficulty of training deep feedforward neural networks[C]//Proceedings of the 13th International Conference on Artificial Intelligence and Statistics, 2010: 249-256.
{{custom_fnGroup.title_cn}}
脚注
{{custom_fn.content}}
基金
国家自然科学基金(61672366)
{{custom_fund}}
PDF(2191 KB)
