融合情感意图和情感原因的共情回复生成方法

doi:10.3778/j.issn.1002-8331.2306-0319

摘要/Abstract

摘要： 共情对话是对话系统研究中的一个重要领域，然而，现有的共情对话研究往往更关注情绪依赖的响应生成，却忽略对话过程中的情感意图信息和情感原因信息，这可能导致生成的共情回复过于通用化或共情性较低，从而降低用户的体验，为了提高共情回复生成的质量，提出了一种融合情感意图和情感原因的共情回复生成方法。通过意图预测模块提取情感意图信息。通过情感原因检测模块提取情感原因信息。在回复生成模块进行意图嵌入和情绪嵌入，并引入情感原因门控机制和复制机制，动态地选择情感原因信息和情感意图信息，促使模型生成与意图相关并且情感合适的共情回复。在EmpatheticDialogues数据集上的实验表明，该方法生成的回复在多样性和共情性方面得到了一定的提升。

关键词: 共情回复, 情感意图, 情感原因, 门控机制, 复制机制

Abstract: Empathetic dialogue is an important area of research in dialogue systems. However, current studies on empathetic dialogue tend to focus more on generating emotion-dependent responses, while overlooking the inclusion of emotional intent and emotional cause information during the dialogue process. This may result in overly generic or less empathetic responses, leading to a diminished user experience. To enhance the quality of empathetic response generation, a novel approach is proposed that integrates emotional intent and emotional cause. Firstly, the intent prediction module is employed to extract emotional intent information. Secondly, the emotional cause detection module is utilized to capture emotional cause information. Lastly, the response generation module incorporates intent embedding and emotion embedding, and introduces a gate mechanism for emotional cause and a copying mechanism. This enables dynamic selection of emotional cause and emotional intent information, facilitating the generation of empathetic responses that are relevant to the intent and emotionally appropriate. Experimental results on the EmpatheticDialogues dataset demonstrate significant improvements in both response diversity and empathetic quality achieved by the proposed method.

Key words: empathetic responses, emotional intent, emotional cause, gate mechanism, copy mechanism

王宁喆, 唐宏, 朱传润, 刘钟. 融合情感意图和情感原因的共情回复生成方法[J]. 计算机工程与应用, 2024, 60(19): 148-157.

WANG Ningzhe, TANG Hong, ZHU Chuanrun, LIU Zhong. Method for Generating Empathetic Responses by Integrating Emotional Intent and Emotional Cause[J]. Computer Engineering and Applications, 2024, 60(19): 148-157.

参考文献

[1] KLEIN J T. Computer response to user frustration[D]. Cambridge: Massachusetts Institute of Technology, 1998.
[2] LIU K, PICARD R W. Embedded empathy in continuous, interactive health assessment[C]//Proceedings of the CHI Workshop on HCI Challenges in Health Assessment, 2005.
[3] BRAVE S, NASS C, HUTCHINSON K. Computers that care: investigating the effects of orientation of emotion exhibited by an embodied computer agent[J]. International Journal of Human-Computer Studies, 2005, 62(2): 161-178.
[4] FITZPATRICK K K, DARCY A, VIERHILE M. Delivering cognitive behavior therapy to young adults with symptoms of depression and anxiety using a fully automated conversational agent (Woebot): a randomized controlled trial[J]. JMIR Mental Health, 2017, 4(2): e7785.
[5] LIU S, ZHENG C, DEMASI O, et al. Towards emotional support dialog systems[J]. arXiv:2106.01144, 2021.
[6] 陈晨, 朱晴晴, 严睿, 等. 基于深度学习的开放领域对话系统研究综述[J]. 计算机学报, 2019, 42(7): 1439-1466.
CHEN C, ZHU Q Q, YAN R, et al. Surver on deep learning based open domain dialogue system[J]. Chinese Journal of Computers, 2019, 42(7): 1439-1466.
[7] 唐宏, 彭金枝, 郭艳霞, 等. 融合主题预测和情感推理的共情回复生成方法[J]. 计算机工程与应用, 2023, 59(14): 114-123.
TANG H, PENG J Z, GUO Y X, et al. Empathetic response generation by integrating topic prediction and emotion reasoning[J]. Computer Engineering and Applications, 2023, 59(14): 114-123.
[8] LIN Z, MADOTTO A, SHIN J, et al. MoEL: mixture of empathetic listeners[C]//Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP), 2019: 121-132.
[9] MAJUMDER N, HONG P, PENG S, et al. MIME: MIMicking emotions for empathetic response generation[C]//Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing, 2020: 8968-8979.
[10] GAO J, LIU Y, DENG H, et al. Improving empathetic response generation by recognizing emotion cause in conversations[C]//Proceedings of the Findings of the Association for Computational Linguistics: EMNLP 2021, 2021: 807-819.
[11] LI Q, CHEN H, REN Z, et al. Multi-resolution interactive empathetic dialogue generation[J]. arXiv:1911.08698, 2019.
[12] LI Q, LI P, CHEN Z, et al. Towards empathetic dialogue generation over multi-type knowledge[J]. arXiv:2009.09708, 2020.
[13] ZHOU X, WANG W Y. MOJITALK: generating emotional responses at scale[C]//Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), 2018: 1128-1137.
[14] ZHOU H, HUANG M, ZHANG T, et al. Emotional chatting machine: emotional conversation generation with internal and external memory[C]//Proceedings of the AAAI Conference on Artificial Intelligence, 2018.
[15] HUANG C, ZAIANE O R, TRABELSI A, et al. Automatic dialogue generation with expressed emotions[C]//Proceedings of the 2018 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 2 (Short Papers), 2018: 49-54.
[16] COLOMBO P, WITON W, MODI A, et al. Affect-driven dialog generation[C]//Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies(Volume 1: Long and Short Papers), 2019: 3734-3743.
[17] SONG Z, ZHENG X, LIU L, et al. Generating responses with a specific emotion in dialog[C]//Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics, 2019: 3685-3695.
[18] SHEN L, FENG Y. CDL: curriculum dual learning for emotion-controllable response generation[C]//Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics, 2020: 556-566.
[19] RASHKIN H, SMITH E M, LI M, et al. Towards empathetic open-domain conversation models: a new benchmark and dataset[C]//Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics, 2019:5370-5381.
[20] ZHAO T, ZHAO R, ESKENAZI M. Learning discourse-level diversity for neural dialog models using conditional variational autoencoders[C]//Proceedings of the 55th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), 2017: 654-664.
[21] ZHAO T, LEE K, ESKENAZI M. Unsupervised discrete sentence representation learning for interpretable neural dialog generation[C]//Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), 2018: 1098-1107.
[22] SHIN J, XU P, MADOTTO A, et al. Generating empathetic responses by looking ahead the user’s sentiment[C]//Proceedings of the 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), 2020: 7989-7993.
[23] LI Q, CHEN H, REN Z, et al. EmpDG: multi-resolution interactive empathetic dialogue generation[C]//Proceedings of the 28th International Conference on Computational Linguistics, 2020: 4454-4466.
[24] WELIVITA A, PU P. A taxonomy of empathetic response intents in human social conversations[C]//Proceedings of the 28th International Conference on Computational Linguistics, 2020: 4886-4899.
[25] WANG J, LI W, LIN P, et al. Empathetic response generation through graph-based multi-hop reasoning on emotional causality[J]. Knowledge-Based Systems, 2021, 233: 107547.
[26] WANG Y H, HSU J H, WU C H, et al. Transformer-based empathetic response generation using dialogue situation and advanced-level definition of empathy[C]//Proceedings of the 2021 12th International Symposium on Chinese Spoken Language Processing (ISCSLP), 2021: 1-5.
[27] LI Q, LI P, REN Z, et al. Knowledge bridging for empathetic dialogue generation[C]//Proceedings of the AAAI Conference on Artificial Intelligence, 2022: 10993-11001.
[28] ZHU L Y, ZHANG Z, WANG J, et al. Multi-party empathetic dialogue generation: a new task for dialog systems[C]//Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), 2022: 298-307.
[29] YAN X, YANG J, SOHN K, et al. Attribute2Image: conditional image generation from visual attributes[C]//Proceedings of the 14th European Conference on Computer Vision, Amsterdam, The Netherlands, Oct 11-14, 2016: 776-791.
[30] GU X, CHO K, HA J W, et al. DialogWAE: multimodal response generation with conditional Wasserstein auto-encoder[C]//Proceedings of the 7th International Conference on Learning Representations, 2019.
[31] BOWMAN S R, VILNIS L, VINYALS O, et al. Generating sentences from a continuous space[J]. arXiv:1511.06349, 2015.
[32] ZANDIE R, MAHOOR M H. Emptransfo: a multi-head transformer architecture for creating empathetic dialog systems[J]. arXiv:2003.02958, 2020.
[33] LIU Y, GAO J, DU J, et al. Empathetic response generation with state management[J]. arXiv:2205.03676, 2022.
[34]P APINENI K, ROUKOS S, WARD T, et al. BLEU: a method for automatic evaluation of machine translation[C]//Proceedings of the 40th Annual Meeting of the Association for Computational Linguistics, 2002: 311-318.
[35] BAHL L R, JELINEK F, MERCER R L. A maximum likelihood approach to continuous speech recognition[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 1983(2): 179-190.
[36] LI J, GALLEY M, BROCKETT C, et al. A diversity-promoting objective function for neural conversation models[C]//Proceedings of the NAACL-HLT, 2016.
[37] ZHANG T, KISHORE V, WU F, et al. BERTScore: evaluating text generation with BERT[C]//Proceedings of the International Conference on Learning Representations, 2019.
[38] ZUEHLKE D, GEWENIGER T, HEIMANN U, et al. Fuzzy Fleiss-Kappa for comparison of fuzzy classifiers[C]//Proceedings of the European Symposium on Artificial Neural Networks, 2009.