Multi-Task Network for Joint Dialog Act Recognition and Sentiment Classification

doi:10.3778/j.issn.1002-8331.2107-0421

Abstract

Abstract: Dialog act recognition and sentiment classification are two interrelated tasks in dialog system, so these tasks should be jointly modeling and excavate implicit interactive information for improving the accuracy of tasks. However, the dialog contextual information and the mutual interaction information proves two crucial?factor of dialog text. The dialog contextual information shows the relation of target information with contextual utterance. The mutual interaction information shows influence of target in different task. In past studies, both types of information are underutilized. In order to solve this problem, a multi-task graph attention network（M-GAT） is proposed and the model multi-task synergic graph attention network（MSGAT） is built to integrate the dialog contextual information and the mutual interaction information. Experimental results on two public datasets show that this model successfully acquires the two sources of information and achieves the state-of-the-art performance. In addition, this paper combines MSGAT and pre-trained models and achieves well result.

Key words: multi-task learning, sentiment classification, dialog act recognition, multi-task graph attention network, deep learning

摘要： 情感分类与对话行为识别任务常被用在对话系统中联合建模，这种联合建模的方法能够挖掘出对话文本的跨任务隐藏交互信息，提高情感分类与对话行为识别的准确性。然而，在两个任务联合建模时，对话文本有上下文信息和跨任务交互信息，对这两种信息与模型预测准确度之间的关系进行研究，需要将这两种信息协同建模，在过去的研究中对这两种信息的利用并不充分，为解决该问题提出多任务图注意力网络（multi-task graph attention network，MGAT），并且以其为核心模块搭建了多任务协同图注意力网络（multi-task synergic graph attention network，MSGAT），该模型将上下文信息与跨任务信息联合建模，同时完成情感分类与对话行为识别任务。利用两个公开数据集实验，得到了良好的效果，并且对联合模型与预训练模型组合进行了研究。

关键词: 多任务学习, 情感分类, 对话行为别, 多任务图注意力网络, 深度学习

LIN Honghui, LIU Jianhua, ZHENG Zhixiong, HU Renyuan, LUO Yixuan. Multi-Task Network for Joint Dialog Act Recognition and Sentiment Classification[J]. Computer Engineering and Applications, 2023, 59(3): 104-111.

林鸿辉, 刘建华, 郑智雄, 胡任远, 罗逸轩. 联合对话行为识别与情感分类的多任务网络[J]. 计算机工程与应用, 2023, 59(3): 104-111.

References

[1] QIN L，LI Z，CHE W，et al.Co-GAT：a co-interactive graph attention network for joint dialog act recognition and sentiment classification[C]//Proceedings of the AAAI Conference on Artificial Intelligence，2021：13709-13717.
[2] CERISARA C，JAFARITAZEHJANI S，OLUOKUN A，et al.Multi-task dialog act and sentiment recognition on mastodon[J].arXiv：1807.05013，2018.
[3] KIM M，KIM H.Integrated neural network model for identifying speech acts，predicators，and sentiments of dialogue utterances[J].Pattern Recognition Letters，2018，101：1-5.
[4] QIN L，CHE W，LI Y，et al.Dcr-net：a deep co-interactive relation network for joint dialog act recognition and sentiment classification[C]//Proceedings of the AAAI Conference on Artificial Intelligence，2020：8665-8672.
[5] VELICKOVIC P，CUCURULL G，CASANOVA A，et al.Graph attention networks[J].arXiv：1710.10903，2017.
[6] VASWANI A，SHAZEER N，PARMAR N，et al.Attention is all you need[C]//Advances in Neural Information Processing Systems，2017：5998-6008.
[7] HOCHREITER S，SCHMIDHUBER J.Long short-term memory[J].Neural Computation，1997，9（8）：1735-1780.
[8] SCHUSTER M，PALIWAL K K.Bidirectional recurrent neural networks[J].IEEE Transactions on Signal Processing，1997，45（11）：2673-2681.
[9] KINGMA D P，BA J.Adam：a method for stochastic optimization[J].arXiv：1412.6980，2014.
[10] HINTON G E，SRIVASTAVA N，KRIZHEVSKY A，et al.Improving neural networks by preventing co-adaptation of feature detectors[J].arXiv：1207.0580，2012.
[11] KUMAR H，AGARWAL A，DASGUPTA R，et al.Dialogue act sequence labeling using hierarchical encoder with crf[C]//Proceedings of the AAAI Conference on Artificial Intelligence，2018.
[12] CHEN Z，YANG R，ZHAO Z，et al.Dialogue act recognition via crf-attentive structured network[C]//The 41st International ACMSIGIR Conference on Research & Development in Information Retrieval，2018：225-234.
[13] RAHEJA V，TETREAULT J.Dialogue act classification with context-aware self-attention[J].arXiv：1904.02594，2019.
[14] MAJUMDER N，PORIA S，HAZARIKA D，et al.DialogueRNN：an attentive RNN for emotion detection in conversations[C]//Proceedings of the AAAI Conference on Artificial Intelligence，2019.
[15] GHOSAL D，MAJUMDER N，PORIA S，et al.DialogueGCN：a graph convolutional neural network for emotion recognition in conversation[J].arXiv：1908.11540，2019.
[16] QIN L，LIU T，CHE W，et al.A co-interactive transformer for joint slot filling and intent detection[C]//2021 IEEE International Conference on Acoustics，Speech and Signal Processing（ICASSP），2021：8193-8197.
[17] QIN L，XU X，CHE W，et al.AGIF：an adaptive graph-interactive framework for joint multiple intent detection and slot filling[J].arXiv：2004.10087，2020.
[18] QIN L，WEI F，XIE T，et al.GL-GIN：fast and accurate non-autoregressive model for joint multiple intent detection and slot filling[J].arXiv：2106.01925，2021.
[19] DEVLIN J，CHANG M W，LEE K，et al.Bert：pre-training of deep bidirectional transformers for language understanding[J].arXiv：1810.04805，2018.
[20] HOCHREITER S.The vanishing gradient problem during learning recurrent neural nets and problem solutions[J].International Journal of Uncertainty，Fuzziness and Knowledge-Based Systems，1998，6（2）：107-116.