Elamur Research⌕
☰
home / papers / 2022 / MISC: A Mixed Strategy-Aware Model integrating COMET for Emotional Support Conversation

MISC: A Mixed Strategy-Aware Model integrating COMET for Emotional Support Conversation

Paper · 2022 · Quan Tu, Yanran Li, Jianwei Cui et al.

Summary

Emotional support conversation (ESC) aims to help a distressed "seeker" gradually feel better, not just to sound empathetic. The authors argue that earlier empathetic chatbots fall short in two ways. They rely on one emotion label for the whole dialogue, which misses how the seeker's feelings shift from turn to turn. They also rarely plan how to actually reduce distress. MISC, built on blenderbot-small, addresses both problems:

  • Mental state from COMET. It queries COMET, a commonsense generator trained on ATOMIC, with the seeker's situation description and latest utterance. An attention step then filters the noisy knowledge it returns against the dialogue context.
  • Mixed strategies. Instead of choosing one support strategy, it predicts a probability distribution over a learned strategy codebook. The response is conditioned on this weighted blend.

On the ESConv benchmark, MISC was compared with five state-of-the-art empathetic models. In both automatic and human evaluation, it produced more relevant and empathetic replies. Its predicted strategy patterns across conversation stages also resembled human supporters more closely. The work shows that fine-grained, turn-level emotion understanding and soft strategy mixing make support dialogue smoother.

Key points

  • Dataset: ESConv (Liu et al., 2021), where each supporter utterance carries one of 8 roughly evenly distributed support strategies. The model's codebook therefore has m = 8 strategy vectors.
  • The strategy representation follows the codebook idea of VQ-VAE: the predicted strategy probabilities weight the codebook vectors. A sharply peaked distribution reduces this to a single strategy.
  • COMET relations such as xAttr and xReact supply mental-state knowledge at two levels. The situation text gives conversation-level information, and the last post gives utterance-level information. Case studies suggest the two sources complement each other.
  • An ablation replaced the mixed strategy with one-hot strategy selection ("Single"). Single scored slightly higher only on Distinct-1 (4.79 vs 4.41). The mixture was better on BLEU-2 (7.31 vs 6.30), ROUGE-L (17.91 vs 17.01) and METEOR (11.05% vs 10.22%).
  • At every k, MISC's top-k strategy prediction accuracy beats BlenderBot-Joint, and its top-5 accuracy exceeds 80%. Code and data are available at github.com/morecry/MISC.

Our summary of the paper, in our own words — not its text. The work belongs to its authors; read it at the links above.

 Institutions

🎓Renmin University of ChinaBeijing · China35 works · 14,757 citations🔬Beijing Academy of Artificial IntelligenceBeijing · China16 works · 7,166 citations🏢XiaomiBeijing · China3 works · 301 citations

📚 Shelves 6The field of science this work belongs to (OpenAlex fields).Computer Science · 9,086 worksArtificial Intelligence · 8,889 worksArts and Humanities · 9,296 worksLanguage and Linguistics · 9,206 worksPsychology · 798 worksExperimental and Cognitive Psychology · 463 works

🧭 Topics 1Research subjects and languages the work is about.Sentiment & emotion · 608 works

Cite

Cite as Quan Tu, Yanran Li, Jianwei Cui, Bin Wang, Ji-Rong Wen and Rui Yan. 2022. MISC: A Mixed Strategy-Aware Model integrating COMET for Emotional Support Conversation. Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers).

The paper itself, not this page. BibTeX from the library's record of the work. DOI 10.18653/v1/2022.acl-long.25

@inproceedings{tu2022misc,
  title = {{MISC: A Mixed Strategy-Aware Model integrating COMET for Emotional Support Conversation}},
  author = {Quan Tu, Yanran Li, Jianwei Cui, Bin Wang, Ji-Rong Wen and Rui Yan},
  booktitle = {Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)},
  year = {2022},
  doi = {10.18653/v1/2022.acl-long.25},
  url = {https://doi.org/10.18653/v1/2022.acl-long.25}
}

References

56 references, 22 of them with a card of ours. ↗ leads to the work, «find» searches for one we have no id for yet.

  1. Jimmy Lei Ba, Jamie Ryan Kiros, and Geoffrey E Hinton. 2016. Layer normalization. arXiv preprint arXiv:1607.06450.
  2. Lisa Bauer, Yicheng Wang, and Mohit Bansal. 2018. Commonsense for generative multi-hop question answering tasks. In Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing, pages 4220–4230, Brussels, Belgium. Association for Computational Linguistics.
  3. Antoine Bosselut, Hannah Rashkin, Maarten Sap, Chaitanya Malaviya, Asli Celikyilmaz, and Yejin Choi. 2019a. COMET: Commonsense transformers for automatic knowledge graph construction. In Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics, pages 4762– 4779, Floren…
  4. Antoine Bosselut, Hannah Rashkin, Maarten Sap, Chaitanya Malaviya, Asli Celikyilmaz, and Yejin Choi. 2019b. COMET: Commonsense transformers for automatic knowledge graph construction. In Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics, pages 4762– 4779, Floren…
  5. Jiaao Chen, Jianshu Chen, and Zhou Yu. 2019. Incorporating structured commonsense knowledge in story completion. In AAAI. find
  6. Anneke De Graaf, Hans Hoeken, José Sanders, and Johannes WJ Beentjes. 2012. Identification as a mechanism of narrative persuasion. Communication research, 39(6):802–823. find
  7. Michael Denkowski and Alon Lavie. 2014. Meteor universal: Language specific translation evaluation for any target language. In Proceedings of the ninth workshop on statistical machine translation, pages 376–380.
  8. Kathleen Kara Fitzpatrick, Alison M Darcy, and Molly Vierhile. 2017. Delivering cognitive behavior therapy to young adults with symptoms of depression and anxiety using a fully automated conversational agent (woebot): A randomized controlled trial. JMIR Mental Health, 4. find
  9. Joseph L. Fleiss and Jacob Cohen. 1973. The equivalence of weighted kappa and the intraclass correlation coefficient as measures of reliability. Educational and Psychological Measurement, 33:613 – 619. find
  10. Jian Guan, Yansen Wang, and Minlie Huang. 2019. Story ending generation with incremental encoding and commonsense knowledge. In AAAI. find
  11. Haozhe Ji, Pei Ke, Shaohan Huang, Furu Wei, Xiaoyan Zhu, and Minlie Huang. 2020. Language generation with multi-hop reasoning on commonsense knowledge graph. In Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP), pages 725–736, Online. Association for Comp… find
  12. Jiwei Li, Michel Galley, Chris Brockett, Jianfeng Gao, and Bill Dolan. 2016. A diversity-promoting objective function for neural conversation models. In Proceedings of the 2016 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, pag…
  13. Qintong Li, Hongshen Chen, Zhaochun Ren, Pengjie Ren, Zhaopeng Tu, and Zhumin Chen. 2020a. EmpDG: Multi-resolution interactive empathetic dialogue generation. In Proceedings of the 28th International Conference on Computational Linguistics, pages 4454–4466, Barcelona, Spain (Online). International C… find
  14. Qintong Li, Piji Li, Zhumin Chen, and Zhaochun Ren. 2021a. Towards empathetic dialogue generation over multi-type knowledge. In AAAI. find
  15. Shifeng Li, Shi Feng, D. Wang, Kaisong Song, Y. Zhang, and Weichao Wang. 2020b. Emoelicitor: An open domain response generation model with user emotional reaction awareness. In IJCAI. find
  16. Yanran Li, Ke Li, Hongke Ning, Xiaoqiang Xia, Yalong Guo, Chen Wei, Jianwei Cui, and Bin Wang. 2021b. Towards an online empathetic chatbot with emotion causes. Proceedings of the 44th International ACM SIGIR Conference on Research and Development in Information Retrieval. find
  17. Yanran Li, Hui Su, Xiaoyu Shen, Wenjie Li, Ziqiang Cao, and Shuzi Niu. 2017. DailyDialog: A manually labelled multi-turn dialogue dataset. In Proceedings of the Eighth International Joint Conference on Natural Language Processing (Volume 1: Long Papers), pages 986–995, Taipei, Taiwan. Asian Federati…
  18. Yanran Li, Ruixiang Zhang, Wenjie Li, and Ziqiang Cao. 2020c. Hierarchical prediction and adversarial learning for conditional response generation. IEEE Transactions on Knowledge and Data Engineering, pages 1–1. find
  19. Bill Yuchen Lin, Xinyue Chen, Jamin Chen, and Xiang Ren. 2019a. KagNet: Knowledge-aware graph networks for commonsense reasoning. In Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP… find
  20. Chin-Yew Lin. 2004. Rouge: A package for automatic evaluation of summaries. In Text summarization branches out, pages 74–81.
  21. Zhaojiang Lin, Andrea Madotto, Jamin Shin, Peng Xu, and Pascale Fung. 2019b. MoEL: Mixture of empathetic listeners. In Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP), page…
  22. Zhaojiang Lin, Peng Xu, Genta Indra Winata, Zihan Liu, and Pascale Fung. 2020. Caire: An end-to-end empathetic chatbot. In AAAI. find
  23. Zhaojiang Lin, Peng Xu, Genta Indra Winata, Farhad Bin Siddique, Zihan Liu, Jamin Shin, and Pascale Fung. 2019c. Caire: An empathetic neural chatbot. arXiv preprint arXiv:1907.12108. — [arXiv:1907.12108](https://arxiv.org/abs/1907.12108) find
  24. Siyang Liu, Chujie Zheng, Orianna Demasi, Sahand Sabour, Yu Li, Zhou Yu, Yong Jiang, and Minlie Huang. 2021. Towards emotional support dialog systems. In Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Lan…
  25. Ilya Loshchilov and Frank Hutter. 2018. Fixing weight decay regularization in adam. find
  26. Nurul Lubis, S. Sakti, Koichiro Yoshino, and S. Nakamura. 2018. Eliciting positive emotion through affect-sensitive dialogue response generation: A neural network approach. In AAAI. find
  27. Nurul Lubis, Sakriani Sakti, Koichiro Yoshino, and Satoshi Nakamura. 2019. Dialogue model and response generation for emotion improvement elicitation. find
  28. Yukun Ma, Khanh Linh Nguyen, Frank Z Xing, and Erik Cambria. 2020. A survey on empathetic dialogue systems. Information Fusion, 64:50–70. find
  29. Navonil Majumder, Pengfei Hong, Shanshan Peng, Jiankun Lu, Deepanway Ghosal, Alexander Gelbukh, Rada Mihalcea, and Soujanya Poria. 2020. MIME: MIMicking emotions for empathetic response generation. In Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP), pag…
  30. Stefano Mezza, Alessandra Cervone, Evgeny Stepanov, Giuliano Tortoreto, and Giuseppe Riccardi. 2018. ISO-standard domain-independent dialogue act tagging for conversational agents. In Proceedings of the 27th International Conference on Computational Linguistics, pages 3539–3551, Santa Fe, New Mexico…
  31. Todor Mihaylov and Anette Frank. 2018. Knowledgeable reader: Enhancing cloze-style reading comprehension with external commonsense knowledge. In Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 821–832, Melbourne, Australia. Assoc…
  32. Aaron van den Oord, Oriol Vinyals, and Koray Kavukcuoglu. 2017. Neural discrete representation learning. arXiv preprint arXiv:1711.00937. — [arXiv:1711.00937](https://arxiv.org/abs/1711.00937) find
  33. Kishore Papineni, Salim Roukos, Todd Ward, and Wei-Jing Zhu. 2002. Bleu: a method for automatic evaluation of machine translation. In Proceedings of the 40th annual meeting of the Association for Computational Linguistics, pages 311–318.
  34. Debjit Paul and Anette Frank. 2019. Ranking and selecting multi-hop knowledge paths to better predict human needs. In 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), page… find
  35. Shachi Paul, Rahul Goel, and Dilek Z. Hakkani-Tür. 2019. Towards universal dialogue act tagging for task-oriented dialogues. ArXiv, abs/1907.03020.
  36. Baolin Peng, Chenguang Zhu, Chunyuan Li, Xiujun Li, Jinchao Li, Michael Zeng, and Jianfeng Gao. 2020. Few-shot natural language generation for task-oriented dialog. In Findings of the Association for Computational Linguistics: EMNLP 2020, pages 172–182, Online. Association for Computational Linguist…
  37. Hannah Rashkin, Eric Michael Smith, Margaret Li, and Y-Lan Boureau. 2018. I know the feeling: Learning to converse with empathy. find
  38. Hannah Rashkin, Eric Michael Smith, Margaret Li, and Y-Lan Boureau. 2019. Towards empathetic open-domain conversation models: A new benchmark and dataset. In Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics, pages 5370–5381, Florence, Italy. Association for Com… find
  39. Stephen Roller, Emily Dinan, Naman Goyal, Da Ju, Mary Williamson, Yinhan Liu, Jing Xu, Myle Ott, Eric Michael Smith, Y-Lan Boureau, and Jason Weston. 2021. Recipes for building an open-domain chatbot. In Proceedings of the 16th Conference of the European Chapter of the Association for Computational…
  40. Maarten Sap, Ronan Le Bras, Emily Allaway, Chandra Bhagavatula, Nicholas Lourie, Hannah Rashkin, Brendan Roof, Noah A. Smith, and Yejin Choi. 2019. ATOMIC: an atlas of machine commonsense for if-then reasoning. In The Thirty-Third AAAI Conference on Artificial Intelligence, AAAI 2019, The Thirty-Fir… find
  41. Abigail See, Stephen Roller, Douwe Kiela, and Jason Weston. 2019. What makes a good conversation? how controllable attributes affect human judgments. In Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Vol…
  42. Jamin Shin, Peng Xu, Andrea Madotto, and Pascale Fung. 2019. Happybot: Generating empathetic dialogue responses by improving user experience lookahead. arXiv preprint arXiv:1906.08487. — [arXiv:1906.08487](https://arxiv.org/abs/1906.08487) find
  43. Zhenqiao Song, Xiaoqing Zheng, Lu Liu, Mu Xu, and Xuanjing Huang. 2019. Generating responses with a specific emotion in dialog. In Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics, pages 3685–3695, Florence, Italy. Association for Computational Linguistics. find
  44. R. Speer, Joshua Chin, and Catherine Havasi. 2017. Conceptnet 5.5: An open multilingual graph of general knowledge. In AAAI. find
  45. ACM International Conference on Information and Knowledge Management. find
  46. Anuradha Welivita and Pearl Pu. 2020. A taxonomy of empathetic response intents in human social conversations. In Proceedings of the 28th International Conference on Computational Linguistics, pages 4886– 4899, Barcelona, Spain (Online). International Committee on Computational Linguistics. find
  47. Baijun Xie and Chung Hyuk Park. 2021. Empathetic robot with transformer-based dialogue agent. In 2021 18th International Conference on Ubiquitous Robots (UR), pages 290–295. IEEE. find
  48. Can Xu, Wei Wu, and Yuehua Wu. 2018. Towards explainable and controllable open domain dialogue generation with dialogue acts. ArXiv, abs/1807.07255. — [arXiv:1807.07255](https://arxiv.org/abs/1807.07255) find
  49. Dian Yu and Zhou Yu. 2021. MIDAS: A dialog act annotation scheme for open domain HumanMachine spoken conversations. In Proceedings of the 16th Conference of the European Chapter of the Association for Computational Linguistics: Main Volume, pages 1103–1120, Online. Association for Computational Ling…
  50. Houyu Zhang, Zhenghao Liu, Chenyan Xiong, and Zhiyuan Liu. 2020. Grounded conversation generation as guided traverses in commonsense knowledge graphs. In Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics, pages 2031–2043, Online. Association for Computational Li…
  51. Tiancheng Zhao, Ran Zhao, and Maxine Eskenazi. 2017. Learning discourse-level diversity for neural dialog models using conditional variational autoencoders. In Proceedings of the 55th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 654–664, Vancouver, C…
  52. Peixiang Zhong, Di Wang, Pengfei Li, Chen Zhang, Hao Wang, and Chunyan Miao. 2021. CARE: commonsense-aware emotional response generation with latent concepts. In AAAI. find
  53. Hao Zhou, Minlie Huang, T. Zhang, Xiaoyan Zhu, and Bing Liu. 2018a. Emotional chatting machine: Emotional conversation generation with internal and external memory. In AAAI. find
  54. Ashish Vaswani, Noam Shazeer, Niki Parmar, Jakob Uszkoreit, Llion Jones, Aidan N Gomez, Łukasz Kaiser, and Illia Polosukhin. 2017. Attention is all you need. In Advances in neural information processing systems, pages 5998–6008.
  55. Hao Zhou, Tom Young, Minlie Huang, Haizhou Zhao, Jingfang Xu, and Xiaoyan Zhu. 2018b. Commonsense knowledge aware conversation generation with graph attention. In Proceedings of the Twenty-Seventh International Joint Conference on Artificial Intelligence, IJCAI-18, pages 4623–4629. International Joi… find
  56. Wei Wei, J. Liu, X. Mao, G. Guo, Feida Zhu, Pan Zhou, and Y. Hu. 2019. Emotion-aware chat machine: Automatic emotional response generation for human-like emotional interaction. Proceedings of the 28th Xianda Zhou and William Yang Wang. 2018. MojiTalk: Generating emotional responses at scale. In Proc… find

Updated

↑ back to top

This page in Markdown → https://md.research.elamur.ai/free/en/papers/tu-2022-misc-mixed-strategy-aware-model/