Towards Emotional Support Dialog Systems

Liu, Siyang; Zheng, Chujie; DeMasi, Orianna; Sabour, Sahand; Yu, Li; Yu, Zhou; Jiang, Yong; Huang, Minlie

doi:10.18653/v1/2021.acl-long.269

Cited by 86 publications

(69 citation statements)

References 30 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Table 3 shows the dialogue safety classification results of four baseline models and the three variants of Canary ( §4.1). With initial T5 weights of Delphi (Jiang et al, 2021), our Canary outperforms all baseline models. This shows that Delphi delivers the knowledge on common patterns of human moral sense for short snippets of everyday situations, which can provide valuable information for determining ethical implications under dialogue setup.…”

Section: Dialogue Safety Classification Via Canarymentioning

confidence: 96%

See 1 more Smart Citation

ProsocialDialog: A Prosocial Backbone for Conversational Agents

Kim¹,

Yu²,

Jiang³

et al. 2022

Preprint

View full text Add to dashboard Cite

Most existing dialogue systems fail to respond properly to potentially unsafe user utterances by either ignoring or passively agreeing with them. To address this issue, we introduce PROSOCIALDIALOG, the first large-scale multi-turn dialogue dataset to teach conversational agents to respond to problematic content following social norms. Covering diverse unethical, problematic, biased, and toxic situations, PROSOCIALDIALOG contains responses that encourage prosocial behavior, grounded in commonsense social rules (i.e., rules-ofthumb, RoTs). Created via a human-AI collaborative framework, PROSOCIALDIALOG consists of 58K dialogues, with 331K utterances, 160K RoTs, and 497K dialogue safety labels accompanied by free-form rationales.With this dataset, we introduce a dialogue safety detection module, Canary, capable of generating RoTs given conversational context, and a socially-informed dialogue agent, Prost. Empirical results show that Prost generates more socially acceptable dialogues compared to other state-of-the-art language and dialogue models in both in-domain and outof-domain settings. Additionally, Canary effectively guides conversational agents and offthe-shelf language models to generate significantly more prosocial responses. Our work highlights the promise and importance of creating and steering conversational AI to be socially responsible.

show abstract

Section: Dialogue Safety Classification Via Canarymentioning

confidence: 96%

“…Additionally, other works have tackled the problem of detecting and explaining whether a situation was toxic or unethical, but not in multi-turns dialogues (Jiang et al, 2021;Forbes et al, 2020;Zhao et al, 2021;Hendrycks et al, 2021;Qiu et al, 2022;Zhang et al, 2022a;Ziems et al, 2022).…”

Section: Related Workmentioning

confidence: 99%

ProsocialDialog: A Prosocial Backbone for Conversational Agents

Kim¹,

Yu²,

Jiang³

et al. 2022

Preprint

View full text Add to dashboard Cite

show abstract

“…[32] generate meaningful responses with a coherent structure for a post, and express the desired emotion within a unified framework. GLHG [33] aims to capture the global cause, local intentions and dialog history, and model hierarchical relationships between them in the emotional support conversation [34]. However, in psychology, the fundamental reason why human beings behave in the external world is that they take motivation as the starting point.…”

Section: Related Workmentioning

confidence: 99%

CogIntAc: Modeling the Relationships between Intention, Emotion and Action in Interactive Process from Cognitive Perspective

Wei¹,

Hu²,

Xie³

et al. 2022

Preprint

View full text Add to dashboard Cite

Intention, emotion and action are important psychological factors in human activities, which play an important role in the interaction between individuals. How to model the interaction process between individuals by analyzing the relationship of their intentions, emotions, and actions at the cognitive level is challenging. In this paper, we propose a novel cognitive framework of individual interaction. The core of the framework is that individuals achieve interaction through external action driven by their inner intention. Based on this idea, the interactions between individuals can be constructed by establishing relationships between the intention, emotion and action. Furthermore, we conduct analysis on the interaction between individuals and give a reasonable explanation for the predicting results. To verify the effectiveness of the framework, we reconstruct a dataset and propose three tasks as well as the corresponding baseline models, including action abduction, emotion prediction and action generation. The novel framework shows an interesting perspective on mimicking the mental state of human beings in cognitive science.

show abstract

“…Empathy is a desirable trait of human daily conversations that enables individuals to understand, perceive, and respond appropriately to the situation and feelings of others (Keskin 2014). Previous research has demonstrated that empathetic dialogue systems can improve user experience and satisfaction in multiple domains (Fitzpatrick, Darcy, and Vierhile 2017;Liu et al 2021;Wang et al 2021). Hence, it is important to discover ways that allow us to equip open-domain dialogue systems with empathy.…”

Section: Introductionmentioning

confidence: 99%

CEM: Commonsense-Aware Empathetic Response Generation

Sabour

Zheng

Huang

2022

AAAI

Self Cite

View full text Add to dashboard Cite

A key trait of daily conversations between individuals is the ability to express empathy towards others, and exploring ways to implement empathy is a crucial step towards human-like dialogue systems. Previous approaches on this topic mainly focus on detecting and utilizing the user’s emotion for generating empathetic responses. However, since empathy includes both aspects of affection and cognition, we argue that in addition to identifying the user’s emotion, cognitive understanding of the user’s situation should also be considered. To this end, we propose a novel approach for empathetic response generation, which leverages commonsense to draw more information about the user’s situation and uses this additional information to further enhance the empathy expression in generated responses. We evaluate our approach on EMPATHETICDIALOGUES, which is a widely-used benchmark dataset for empathetic response generation. Empirical results demonstrate that our approach outperforms the baseline models in both automatic and human evaluations and can generate more informative and empathetic responses. Our code is available at https://github.com/Sahandfer/CEM.

show abstract

Towards Emotional Support Dialog Systems

Cited by 86 publications

References 30 publications

ProsocialDialog: A Prosocial Backbone for Conversational Agents

ProsocialDialog: A Prosocial Backbone for Conversational Agents

CogIntAc: Modeling the Relationships between Intention, Emotion and Action in Interactive Process from Cognitive Perspective

CEM: Commonsense-Aware Empathetic Response Generation

Contact Info

Product

Resources

About