情感对话生成是近年来自然语言处理任务中的热门方向之一,生成带有情感色彩的响应能提高人机间的互动性。现有的情感对话生成模型情感变量单一,容易生成枯燥的响应。为确保响应语句不仅语义逻辑正确且具有多样性,该文提出了二阶段对话生成模型。第一阶段,利用DialoGPT强大的语言理解能力来确保生成语义正确的响应;为解决响应枯燥单调的缺点,该文提出融合主情感变量和混合情感变量作为全局情感变量用于后续操作;第二阶段,在第一阶段生成的响应基础上,利用全局情感变量对语句进行重写操作,从而生成高质量的响应。实验结果表明,该文提出的模型在Empathetic Dialogues数据集上的响应质量要优于基线模型。
Abstract
Emotional dialogue generation has become one of the popular topics in natural language processing. It can improve the interaction between human and computer, but existing affective dialogue generation models only use a single affective variable and is easy to generate boring responses. To ensure the response sentences are not only semantically correct but also diversified, a two-stage dialogue generation model is proposed in this paper. In the first stage, DialoGPT with its powerful language understanding capabilities are used to ensure that responses with correct semantics can be generated. Main emotional variables and mixed emotional variables are fused to be global emotional variables to deal with the boring response. In the second stage, the global emotional variable is used to rewrite the response generated in the first stage, so as to polish the statement. Experimental results show that the proposed model performs better on the Empathetic Dialogues dataset than the baseline models.
关键词
对话生成 /
二阶段 /
主情感 /
混合情感 /
多样性
{{custom_keyword}} /
Key words
dialogue generation /
two-stage /
main emotion /
mixed emotion /
diversity
{{custom_keyword}} /
{{custom_sec.title}}
{{custom_sec.title}}
{{custom_sec.content}}
参考文献
[1] Xu Y, Zhao H, Zhang Z. Topic-Aware multi-turn dialogue modeling[C]//Proceedings of the AAAI Conference on Artificial Intelligence, 2021, 35(16): 14176-14184.
[2] Xing C, Wu W, Wu Y, et al. Topic aware neural response generation[C]//Proceedings of the AAAI Conference on Artificial Intelligence, 2017.
[3] 李少博, 孙承杰, 徐振, 等. 基于知识拷贝机制的生成式对话模型[J]. 中文信息学报, 2021,35(02): 107-115.
[4] Wu W, Guo Z, Zhou X, et al. Proactive human-machine conversation with explicit conversation goal[C]//Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics,2019: 3794-3804.
[5] Zheng Y, Zhang R, Huang M, et al. A pre-training based personalized dialogue generation model with persona-sparse data[C]//Proceedings of the AAAI Conference on Artificial Intelligence, 2020, 34(05): 9693-9700.
[6] Song H, Wang Y, Zhang W, et al. Generate, delete and rewrite: a three-stage framework for improving persona consistency of dialogue generation[C]//Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics, 2020: 5821-5831.
[7] Prendinger H, Mori J, Ishizuka M. Using human physiology to evaluate subtle expressivity of a virtual quizmaster in a mathematical game[J]. International Journal of Human-computer Studies,2005,62(2): 231-245.
[8] Zech E, Rimé B. Is talking about an emotional experience helpful? Effects on emotional recovery and perceived benefits[J]. Clinical Psychology and Psychotherapy: An International Journal of Theory and Practice, 2005, 12(4): 270-287.
[9] Sutskever I, Vinyals O, Le Q V. Sequence to sequence learning with neural networks[C]//Proceedings of the 27th International Conference on Neural Information Processing Systems, 2014: 3104-3112.
[10] 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.
[11] Zhang Y, Sun S, Galley M, et al. Dialogpt: large-scale generative pre-training for conversational response generation[J]. arXiv preprint arXiv:1911.00536, 2019.
[12] 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.
[13] 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.
[14] Ma Z, Yang R, Du B, et al. A control unit for emotional conversation generation[J]. IEEE Access, 2020, (8): 43168-43176.
[15] 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.
[16] 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: 6000-6010.
[17] Majumder N, Hong P, Peng S, et al. MIME: mimicking emotions for empathetic response generation[C]//Proceedings of the Conference on Empirical Methods in Natural Language Processing,2020: 8968-8979.
[18] Nie L, Wang W, Hong R, et al. Multimodal dialog system: generating responses via adaptive decoders[C]//Proceedings of the 27th ACM International Conference on Multimedia, 2019: 1098-1106.
[19] Radford A, Wu J, Child R, et al. Language models are unsupervised multitask learners[J].OpenAI blog, 2019, 1(8): 9.
[20] Radford A, Narasimhan K, Salimans T, et al. Improving language understanding by generative pre-training[EB/OL]. https://www.cs.ubc.ca/～amuham01/LING530/papers/radford2018improving.pdf[2019-07-16].
[21] 孙五俊, 姜媛, 方平. 混合情绪能促进心理健康吗？[J]. 心理科学, 2021, 44(01): 230-236.
[22] Serban I V, Sordoni A, Lowe R, et al. A hierarchical latent variable encoder-decoder model for generating dialogues[C]//Proceedings of the 31th AAAI Conference on Artificial Intelligence, 2017: 3295-3301.
[23] 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.
[24] Papineni 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.
[25] Bengio Y, Ducharme R, Vincent P, et al. A neural probabilistic language model[J]. Journal of Machine Learning Research, 2003, 3: 1137-1155.
[26] Liu C-W, Lowe R, Serban I, et al. How not to evaluate your dialogue system: an empirical study of unsupervised evaluation metrics for dialogue response generation[C]//Proceedings of the Conference on Empirical Methods in Natural Language Processing, 2016: 2122-2132.
[27] Lin Z, Madotto A, Shin J, et al. MoEL: mixture of empathetic listeners[C]//Proceedings of the Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing, 2019: 121-132.
{{custom_fnGroup.title_cn}}
脚注
{{custom_fn.content}}
基金
宁波市科技计划项目(2019B10032,2021S091)
{{custom_fund}}
PDF(1920 KB)
