Elamur Research
☰
home / papers / 2021 / Towards Emotional Support Dialog Systems

Towards Emotional Support Dialog Systems

Written for the Research library (claude-opus-5-5) from the paper text. Original — aclanthology.org/2021.acl-long.269.pdf

Summary

This ACL-IJCNLP 2021 paper argues that dialog systems lack the ability to provide real emotional support. Earlier work on emotional chatting or empathetic responding only expresses emotion or recognizes feelings. It does not explore a person's problem or help them act on it. The authors define a new task, Emotional Support Conversation (ESC), focused on peer-style support rather than professional therapy. They propose an ESC Framework adapted from Hill's Helping Skills Theory, with three stages (Exploration, Comforting, Action), each tied to specific support strategies. They also build ESConv, a crowdsourced corpus in which trained supporters chat with help-seekers. Every utterance is labelled with the strategy used, and seekers report their emotional state before and after the chat. Supporter tutorials and combined manual and automatic quality filters keep the data reliable. Experiments with state-of-the-art dialog models show that using support strategies clearly improves the support delivered. A strategy-aware Joint model learns to use strategies the way human supporters do. The work gives the field both a task definition and training data for supportive dialog.

Key points

  • The framework's three stages are Exploration, Comforting and Action. Example strategies include Question, Self-disclosure, Reflection of Feelings, Affirmation and Reassurance, and Providing Suggestions.
  • Each help-seeker is described by a negative emotion label, an intensity level (1–5) and an underlying problem. Support counts as effective if the intensity goes down; one sample dialog dropped from 5 to 2.
  • Automatic filtering rules were tuned against three human annotators. A kept conversation requires the supporter to meet at least 3 of 4 criteria and the seeker to meet both of theirs. The final rule reached an average Cohen's Kappa of 0.576 with the human annotators.
  • In a case study, a strategy-aware Joint model stays focused on the user. BlenderBot without fine-tuning often drifts into talking about itself.
  • ESConv data and code are released at github.com/thu-coai/Emotional-Support-Conversation.

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

Fields: Natural language processing

Cited by

175 papers of our library cite it (of the 140673 whose bibliographies we read); 2 of them have a page here, 173 not yet.

Cite

The paper itself, not this page. BibTeX from the library's record of the work. DOI 10.18653/v1/2021.acl-long.269

@inproceedings{liu2021emotional,
  title = {{Towards Emotional Support Dialog Systems}},
  author = {Liu, Siyang and Zheng, Chujie and Demasi, Orianna and Sabour, Sahand and Li, Yu and Yu, Zhou and Jiang, Yong and Huang, Minlie},
  booktitle = {Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (Volume 1: Long Papers)},
  year = {2021},
  doi = {10.18653/v1/2021.acl-long.269},
  url = {https://doi.org/10.18653/v1/2021.acl-long.269}
}

References

40 references, 7 of them with a card of ours. ↗ leads to the work, «find» searches for one we have no id for yet.

  1. In this work, we define the task of Emotional Support Conversation and present an ESC Framework. The ESC Framework is adapted from the Helping Skills Theory into a dialog system setting, which characterizes three stages with corresponding support strategies useful at each stage. We then construct an… find
  2. Brant R Burleson. 2003. Emotional support skill. HANDBOOK OF COMMUNICATION AND SO-CIAL INTERACTION SKILLS, page 551. find
  3. Jacob Cohen. 1960. A coefficient of agreement for nominal scales. Educational and psychological measurement, 20(1):37–46. find
  4. Catherine A Heaney and Barbara A Israel. 2008. Social networks and social support. Health behavior and health education: Theory, research, and practice, 4:189–210. find
  5. Clara E Hill. 2009. Helping skills: Facilitating, exploration, insight, and action. American Psychological Association. find
  6. Ari Holtzman, Jan Buys, Li Du, Maxwell Forbes, and Yejin Choi. 2019. The curious case of neural text degeneration. In International Conference on Learning Representations. find
  7. Mahshid Hosseini and Cornelia Caragea. 2021. It takes two to empathize: One to seek and one to provide. Proceedings of the 35th American Association for Artificial Intelligence (AAAI 2021). find
  8. Minlie Huang, Xiaoyan Zhu, and Jianfeng Gao. 2020. Challenges in building intelligent open-domain dialog systems. ACM Transactions on Information Systems (TOIS), 38(3):1–32. find
  9. Bernd Huber, Daniel McDuff, Chris Brockett, Michel Galley, and Bill Dolan. 2018. Emotional dialogue generation using image-grounded language models. In Proceedings of the 2018 CHI Conference on Human Factors in Computing Systems, pages 1–12. find
  10. Diederik P Kingma and Jimmy Ba. 2014. Adam: A method for stochastic optimization. arXiv preprint arXiv:1412.6980. find
  11. Catherine Penny Hinson Langford, Juanita Bowsher, Joseph P Maloney, and Patricia P Lillis. 1997. Social support: a conceptual analysis. Journal of advanced nursing, 25(1):95–100. find
  12. 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… find our card
  13. Chin-Yew Lin. 2004. ROUGE: A package for automatic evaluation of summaries. In Text Summarization Branches Out, pages 74–81, Barcelona, Spain. Association for Computational Linguistics. find
  14. Zhaojiang Lin, Andrea Madotto, Jamin Shin, Peng Xu, and Pascale Fung. 2019. 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), pages… find
  15. Chia-Wei Liu, Ryan Lowe, Iulian Serban, Mike Noseworthy, Laurent Charlin, and Joelle Pineau. 2016. How NOT to evaluate your dialogue system: An empirical study of unsupervised evaluation metrics for dialogue response generation. In Proceedings of the 2016 Conference on Empirical Methods in Natural L… find
  16. Edward Loper and Steven Bird. 2002. Nltk: the natural language toolkit. arXiv preprint cs/0205028. find
  17. 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… find
  18. Lenin Medeiros and Tibor Bosse. 2018. Using crowdsourcing for the development of online emotional support agents. In International Conference on Practical Applications of Agents and Multi-Agent Systems, pages 196–209. Springer. find
  19. Burt L Monroe, Michael P Colaresi, and Kevin M Quinn. 2008. Fightin’words: Lexical feature selection and evaluation for identifying the content of political conflict. Political Analysis, 16(4):372–403. find
  20. 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, Philadelphia, Pennsylvania, USA. Association for Computational… find our card
  21. Alec Radford, Jeffrey Wu, Rewon Child, David Luan, Dario Amodei, and Ilya Sutskever. 2019. Language models are unsupervised multitask learners. OpenAI blog, 1(8):9. find
  22. Stephen A Rains, Corey A Pavlich, Bethany Lutovsky, Eric Tsetsi, and Anjali Ashtaputre. 2020. Support seeker expectations, support message quality, and supportive interaction processes and outcomes: The case of the comforting computer program revisited. Journal of Social and Personal Relationships,… find
  23. 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
  24. Stephen Roller, Emily Dinan, Naman Goyal, Da Ju, Mary Williamson, Yinhan Liu, Jing Xu, Myle Ott, Kurt Shuster, Eric M Smith, et al. 2020. Recipes for building an open-domain chatbot. arXiv preprint arXiv:2004.13637. find our card
  25. Ashish Sharma, Adam Miner, David Atkins, and Tim Althoff. 2020a. A computational approach to understanding empathy expressed in text-based mental health support. In Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP), pages 5263–5276, Online. Association fo… find our card
  26. Ashish Sharma, Adam S Miner, David C Atkins, and Tim Althoff. 2020b. A computational approach to understanding empathy expressed in text-based mental health support. arXiv preprint arXiv:2009.08441. find our card
  27. Shikhar Sharma, Layla El Asri, Hannes Schulz, and Jeremie Zumer. 2017. Relevance of unsupervised metrics in task-oriented dialogue for evaluating natural language generation. arXiv preprint arXiv:1706.09799. — [arXiv:1706.09799](https://arxiv.org/abs/1706.09799) find
  28. Siqi Shen, Charles Welch, Rada Mihalcea, and Verónica Pérez-Rosas. 2020. Counseling-style reflection generation using generative pretrained transformers with augmented context. In Proceedings of the 21th Annual Meeting of the Special Interest Group on Discourse and Dialogue, pages 10–20, 1st virtual… find
  29. Hao Sun, Zhenru Lin, Chujie Zheng, Siyang Liu, and Minlie Huang. 2021. Psyqa: A chinese dataset for generating long counseling text for mental health support. In Findings of the Association for Computational Linguistics: ACL 2021. find
  30. Janneke M van der Zwaan, Virginia Dignum, and Catholijn M Jonker. 2012. A conversation model enabling intelligent agents to give emotional support. In Modern Advances in Intelligent Systems and Tools, pages 47–52. Springer. find
  31. JM Van der Zwaan, V Dignum, and CM Jonker. 2012. A bdi dialogue agent for social support: Specification and evaluation method. In AAMAS 2012: Proceedings of the 11th International Conference on Autonomous Agents and Multiagent Systems, Workshop on Emotional and Empathic Agents, Valencia, Spain, 4-8… find
  32. Charles Welch, Allison Lahnala, Veronica Perez-Rosas, Siqi Shen, Sarah Seraj, Larry An, Kenneth Resnicow, James Pennebaker, and Rada Mihalcea. 2020. Expressive interviewing: A conversational system for coping with COVID-19. In Proceedings of the 1st Workshop on NLP for COVID-19 (Part 2) at EMNLP 202… find
  33. Thomas Wolf, Lysandre Debut, Victor Sanh, Julien Chaumond, Clement Delangue, Anthony Moi, Pier-ric Cistac, Tim Rault, Remi Louf, Morgan Funtowicz, Joe Davison, Sam Shleifer, Patrick von Platen, Clara Ma, Yacine Jernite, Julien Plu, Canwen Xu, Teven Le Scao, Sylvain Gugger, Mariama Drame, Quentin Lho… find our card
  34. Rohola Zandie and Mohammad H Mahoor. 2020. Emptransfo: A multi-head transformer architecture for creating empathetic dialog systems. arXiv preprint arXiv:2003.02958. — [arXiv:2003.02958](https://arxiv.org/abs/2003.02958) find
  35. Yizhe Zhang, Siqi Sun, Michel Galley, Yen-Chun Chen, Chris Brockett, Xiang Gao, Jianfeng Gao, Jingjing Liu, and Bill Dolan. 2020. DIALOGPT : Large-scale generative pre-training for conversational response generation. In Proceedings of the 58th Annual Meeting of the Association for Computational Ling… find our card
  36. Chujie Zheng, Yong Liu, Wei Chen, Yongcai Leng, and Minlie Huang. 2021. Comae: A multi-factor hierarchical framework for empathetic response generation. In Findings of the Association for Computational Linguistics: ACL 2021. find
  37. Peixiang Zhong, Chen Zhang, Hao Wang, Yong Liu, and Chunyan Miao. 2020. Towards persona-based empathetic conversational models. In Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP), pages 6556–6566, Online. Association for Computational Linguistics. find
  38. Hao Zhou, Minlie Huang, Tianyang Zhang, Xiaoyan Zhu, and Bing Liu. 2018. Emotional chatting machine: Emotional conversation generation with internal and external memory. In Proceedings of the AAAI Conference on Artificial Intelligence. find
  39. Li Zhou, Jianfeng Gao, Di Li, and Heung-Yeung Shum. 2020. The design and implementation of xiaoice, an empathetic social chatbot. Computational Linguistics, 46(1):53–93. find
  40. Xianda Zhou and William Yang Wang. 2018. MojiTalk: Generating emotional responses at scale. In Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 1128–1137, Melbourne, Australia. Association for Computational Linguistics. find