Towards Emotional Support Dialog Systems

By Siyang Liu, Chujie Zheng, Orianna DeMasi, Sahand Sabour, Yu Li, Zhou Yu, Yong Jiang, Minlie Huang. Annual Meeting of the Association for Computational Linguistics, 2021

460 citations recorded by the source corpus.

Emotional support is a crucial ability for many conversation scenarios, including social interactions, mental health support, and customer service chats. Following reasonable procedures and using various support skills can help to effectively provide support. However, due to the lack of a well-designed task and corpora of effective emotional support conversations, research on building emotional support into dialog systems remains lacking. In this paper, we define the Emotional Support Conversation (ESC) task and propose an ESC Framework, which is grounded on the Helping Skills Theory. We construct an Emotion Support Conversation dataset (ESConv) with rich annotation (especially support strategy) in a help-seeker and supporter mode. To ensure a corpus of high-quality conversations that provide examples of effective emotional support, we take extensive effort to design training tutorials for supporters and several mechanisms for quality control during data collection. Finally, we evaluate state-of-the-art dialog models with respect to the ability to provide emotional support. Our results show the importance of support strategies in providing effective emotional support and the utility of ESConv in training more emotional support systems.

Subfields: Artificial Intelligence, Social Psychology

View Paper: https://www.semanticscholar.org/paper/96e7f77ed0101ac3c7c4dc41601563ce0bc8889b

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

1. Yejin Choi
2. Minlie Huang
3. Ximing Lu
4. Daniel Khashabi
5. Xiaoyan Zhu
6. Mohit Bansal
7. Maarten Sap
8. Chujie Zheng

In Social Psychology

1. Yejin Choi
2. Xiaoyan Zhu
3. Minlie Huang
4. Maarten Sap

Citations in the corpus

• The Moral Integrity Corpus: A Benchmark for Ethical Dialogue Systems (2022, unknown): ““chit chat” settings (Brandtzaeg and Følstad, 2017; Huang et al., 2020; Liu et al., 2021b) and in many other more structured domains (Gao et al.”
• ProsocialDialog: A Prosocial Backbone for Conversational Agents (2022, background): “…with positive elements such as affective aspects (e.g., emotion, persona, empathy) (Li et al., 2017; Zhang et al., 2018; Rashkin et al., 2019; Liu et al., 2021), intellectual aspects (e.g., Wikipedia knowledge) (Dinan et al., 2018; Moghe et al., 2018; Gopalakrish-nan et al., 2019; Komeili et…”
• EVA2.0: Investigating Open-domain Chinese Dialogue Systems with Large-scale Pre-training (2022, background): “, 2021) to the high-level support strategies (Liu et al., 2021; Sun et al., 2021a).”
• Exploring Prompt-based Few-shot Learning for Grounded Dialog Generation (2021, methodology): “For instance, (Zhao et al., 2020b; Liu et al., 2021b) prepend input sequences with special tokens as SI or GS, which is essentially a simple yet basic soft-prompting method and is also adopted in recent works of prompt-based learning (Liu et al.”
• APTNESS: Incorporating Appraisal Theory and Emotion Support Strategies for Empathetic Response Generation (2024, methodology): “Previous research has demonstrated that incorporating these strategies can effectively guide models in generating empathetic responses [14, 32].”