Abstract：Dialog sentiment analysis aims to classify the sentiment of each sentence in a dialogue, considering both the speaker’s personal emotion and the emotion transmission between speakers. To model this with Transformer, this paper proposes a multi-party attention mechanism to better model the interaction between different speakers and simulate dialogue scenes. Experiments show that, compared with other SOTA models, Dialogue Transformer has simpler implementation, faster running speed, and an significantly increased Weighted-F1 value.
[1] Collobert R, Weston J, Bottou L, et al. Naturallanguage pocessing (almost) from sratch[J]. Journal of Machine Learning Research, 2011, 12(1): 2493-2537. [2] David O. Fromuterance to text: The bias of language in speech and writing[J]. Harvard Educational Review, 1977, 47(3): 257-281. [3] Morris M W, Keltner D. How emotions work: The social functions of emotional expression in negotiations[J]. Research in Organizational Behavior, 2000, 22: 1-50. [4] Koval P, Kuppens P. Changing emotion dynamics: Individual differences in the effect of anticipatory social stress on emotional inertia.[J]. Emotion, 2012, 12(2): 256-267. [5] Hazarika D, Poria S, Zadeh A, et al. Conversational memory network for emotion recognition in dyadic dialogue videos[C]//Proceedings of the Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, 2018: 2122-2132. [6] Cho K, Van Merrienboer B, Gulcehre C, et al. Learningphrase representations using RNN encoder-decoder for statistical machine translation[C]//Proceedings of the Conference on Empirical Methods in Natural Language Processing, 2014: 1724-1734. [7] Hazarika D, Poria S, Mihalcea R, et al. ICON: Interactive conversational memory network for multimodal emotion detection[C]//Proceedings of the Conference on Empirical Methods in Natural Language Processing, 2018: 2594-2604. [8] Majumder N, Poria S, Hazarika D, et al. Dialogue RNN: anattentive RNN for emotion detection in conversations[C]//Proceedings of the AAAI Conference on Artificial Intelligence, 2019: 6818-6825. [9] Dzmitry B, Kyunghyun C, Yoshua B. Neural machine translation by jointly learning to align and translate[J]. CoRR, abs/1409.0473, 2014. [10] 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, 2017: 5998-6008. [11] Jonas G, Michael A, David G,et al. Convolutional sequence to sequence learning[J]. arXiv preprint arXiv: 1705.03122v2, 2017. [12] He K, Zhang X, Ren S, et al. Deep residual learning for image recognition[C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2016: 770-778. [13] Cambria E, Das D, Bandyopadhyay S, et al. A practical guide to sentiment analysis[M]. Springer, 2017. [14] Rao Y, Lei J, Wenyin L, et al. Building emotional dictionary for sentiment analysis of online news[J]. World Wide Web, 2014, 17(4): 723-742. [15] Ahmad M, Aftab S, Ali I. Sentiment analysis of tweets using SVM[J].InternationalJournal of Computer Applications, 2017, 177(5): 25-29. [16] Dey L, Chakraborty S, Biswas A, et al. Sentiment analysis of review datasets using naive bayes and k-nn classifier[J]. arXiv preprint arXiv: 1610.09982, 2016. [17] Poria S, Cambria E, Hazarika D, et al. Context-dependent sentiment analysis in user-generated videos[C]//Proceedings of the 55th Annual Meeting of the Association for Computational Linguistics,2017: 873-883. [18] Naseem U, Razzak I, Musial K, et al. Transformer based deep intelligent contextual embedding for twitter sentiment analysis[J]. Future Generation Computer Systems, 2020, 113(2020): 58-69. [19] Mikolov T, Chen K, Corrado G, et al. Efficient estimation of word representations in vector space[J]. arXiv preprint arXiv: 1301.3781, 2013. [20] Ambartsoumian A, Popowich F. Self-attention: A better building block for sentiment analysis neural network classifiers[J]. arXiv preprint arXiv: 1812.07860, 2018. [21] Li Y, Su H, Shen X, et al. Dailydialog: A manually labelled multi-turn dialogue dataset[C]//Proceedings of the 8th International Joint Conference on Natural Language Processing, 2017: 986-995. [22] Poria S, Hazarika D, Majumder N, et al. MELD: Amultimodal multi-party dataset for emotion recognition in conversations[C]//Proceedings of the 57th Conference of the Association for Computational Linguistics, 2018: 527-536.
2022, Vol. 36 
