Emotional Intensity Response Generation Model

doi:10.3778/j.issn.1673-9418.2301045

Abstract

Abstract: Emotional dialogue generation models do not consider the emotional intensity factor in response generation, which leads to the inappropriateness of the emotional expression in generated response, and reduces the user interaction experience. Inspired by the work of emotional intensity in emotional psychology, this paper proposes an emotional intensity response generation model (EIRGM), which includes an emotional intensity prediction unit, a context encoding module and an emotional intensity response generation unit. An emotional intensity prediction unit provides emotion categories and emotional intensity for reply sentences; a context encoding module provides content basis for response; an emotional intensity response generation unit is used to express the emotion and intensity in response. Based on the NLPCC2018 open-domain dialogue dataset, experiments are carried out in terms of emotional appropriateness, emotional intensity appropriateness, content relevance, and dialogue persistence. Experimental results show that EIRGM is not much different from the optimal model in terms of emotional appropriateness, and EIRGM is improved by 4.1 percentage points and 0.8 percentage points compared with the optimal model in terms of emotional intensity appropriateness and dialogue persistence, respectively. It shows that the model improves the emotional intensity appropriateness of emotional expression, and improves the user’s willingness to interact.

Key words: emotional intensity, emotion categories, emotional dialogue, response generation, emotional expression

摘要： 情感对话生成模型在回复生成中未考虑情感强度因素，导致生成回复的情感表达存在波动不恰当性，降低用户交互体验。受情绪心理学中情感强度工作的启发，提出一种情感强度回复生成模型（EIRGM）。模型包括情感强度预测单元、语境编码模块和情感强度回复生成单元，其中情感强度预测单元为回复语句提供情感类别和情感强度，语境编码模块单元为回复语句提供内容基础，情感强度回复生成单元构成用于回复语句中情感和强度的表达。实验以NLPCC2018开放域对话数据集为基础，开展了情感恰当性、情感强度恰当性、内容关联性以及对话持续性等实验。实验结果表明，EIRGM在情感恰当性方面与最优模型相差不大，在情感强度恰当性和对话持续性方面与最优模型相比分别提升4.1个百分点和0.8个百分点，表明了EIRGM模型在提升情感强度表达恰当性同时也提高了用户交互意愿。

关键词: 情感强度, 情感类别, 情感对话, 回复生成, 情感表达

MA Zhiqiang, ZHOU Yutong, JIA Wenchao, XU Biqi, WANG Chunyu. Emotional Intensity Response Generation Model[J]. Journal of Frontiers of Computer Science and Technology, 2024, 18(5): 1339-1347.

马志强, 周钰童, 贾文超, 许璧麒, 王春喻. 情感强度回复生成模型[J]. 计算机科学与探索, 2024, 18(5): 1339-1347.

References

[1] LI D, LI Y, WANG S. Interactive double states emotion cell model for textual dialogue emotion prediction[J]. Knowledge-Based Systems, 2020, 189: 105084.
[2] GHOSH S, CHOLLET M, LAKSANA E, et al. Affect-LM: a neural language model for customizable affective text generation[J]. arXiv:1704.06851, 2017.
[3] FIRDAUS M,?CHAUHAN H,?EKBAL A, et al. MEISD: a multimodal multi-label emotion, intensity and sentiment dialogue dataset for emotion recognition and sentiment analysis in conversations[C]//Proceedings of the 28th International Conference on Computational Linguistics, Barcelona, Dec 8-12, 2020: 4441-4453.
[4] GRAVES A. Long short-term memory: supervised sequence labelling with recurrent neural networks[J]. Studies in Computational Intelligence, 2012, 385: 37-45.
[5] CHO K, VAN MERRI?NBOER B, GULCEHRE C, et al. Learning phrase representations using RNN encoder-decoder for statistical machine translation[J]. arXiv:1406.1078, 2014.
[6] ZAREMBA W, SUTSKEVER I, VINYALS O. Recurrent neural network regularization[J]. arXiv:1409.2329, 2014.
[7] LI J, GALLEY M, BROCKETT C, et al. A diversity-promoting objective function for neural conversation models[J]. arXiv:1510.03055, 2015.
[8] SORDONI A, BENGIO Y, VAHABI H, et al. A hierarchical recurrent encoder-decoder for generative context-aware query suggestion[C]//Proceedings of the 24th ACM International Conference on Information and Knowledge Management, May 1-8, 2015. New York: ACM, 2015: 553-562.
[9] SERBAN I, SORDONI A, LOWE R, et al. A hierarchical latent variable encoder-decoder model for generating dialogues[C]//Proceedings of the 2017 AAAI Conference on Artificial Intelligence, San Francisco, Feb 2-7, 2017. Menlo Park: AAAI, 2017: 3295-3301.
[10] XING C, WU Y, WU W, et al. Hierarchical recurrent attention network for response generation[C]//Proceedings of the 32nd AAAI Conference on Artificial Intelligence, the 30th Innovative Applications of Artificial Intelligence, and the 8th AAAI Symposium on Educational Advances in Artificial Intelligence, New Orleans, Feb 2-7, 2018. Menlo Park: AAAI, 2018: 5610-5617.
[11] ZHOU H, HUANG M, ZHANG T, et al. Emotional chatting machine: emotional conversation generation with internal and external memory[C]//Proceedings of the 32nd AAAI Conference on Artificial Intelligence, New Orleans, Feb 2-7, 2018. Menlo Park: AAAI, 2018: 730-738.
[12] CHEN Z, SONG R, XIE X, et al. Neural response generation with relevant emotions for short text conversation[C]// Proceedings of the 2019 CCF International Conference on Natural Language Processing and Chinese Computing, Dun-huang, Oct 9-14, 2019. Cham: Springer, 2019: 117-129.
[13] YAO K C, ZHANG L B, LUO T J, et al. Non-deterministic and emotional chatting machine: learning emotional conversation generation using conditional variational autoencoders[J]. Neural Computing and Applications, 2021, 33(11): 5581-5589.
[14] MA Z Q, DU B X, SHEN J, et al. A emotional and context-sensitive model for the Seq2Seq-based dialogue generation[J]. Elektrotehni?ki Vestnik, 2020, 87(3): 127-134.
[15] LI Q T, LI P J, REN Z, et al. Knowledge bridging for empathetic dialogue generation[C]//Proceedings of the 36th AAAI Conference on Artificial Intelligence, Feb 22-Mar 1, 2022. Menlo Park: AAAI, 2022: 10993-11001.
[16] SABOUR S, ZHENG C, HUANG M. CEM: commonsense-aware empathetic response generation[C]//Proceedings of the 36th AAAI Conference on Artificial Intelligence, Feb 22-Mar 1, 2022. Menlo Park: AAAI, 2022: 11229-11237.
[17] WANG C, MA Z, JIA W, et al. Specify the emotional intensity response generation model[C]//Proceedings of the 5th International Conference on Pattern Recognition and Artificial Intelligence, Chengdu, Aug 18-12, 2022. Piscataway: IEEE, 2022: 994-1001.
[18] PASZKE A, GROSS S, MASSA F, et al. Pytorch: an imperative style, high-performance deep learning library[C]//Proc-eedings of the 33rd International Conference on Neural Information Processing Systems. Red Hook: Curran Associates, 2019: 8026-8037.
[19] RADFORD A, WU J, CHILD R, et al. Language models are unsupervised multitask learners[J]. OpenAI Blog, 2019, 1(8): 9.
[20] SHAN Y, CUI A, TAN L, et al. Overview of the NLPCC 2019 shared task: open domain conversation evaluation[C]//Proceedings of the 8th CCF International Conference on Nat-ural Language Processing and Chinese Computing, Dunhuang, Oct 9-14, 2019. Cham: Springer, 2019: 829-834.