PsyQA: A Chinese Dataset for Generating Long Counseling Text for Mental Health Support

Sun, Hao; Lin, Zhenru; Zheng, Chujie; Liu, Siyang; Huang, Minlie

doi:10.18653/v1/2021.findings-acl.130

Cited by 24 publications

(15 citation statements)

References 26 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…If the dialogue system fails to respond correctly, the seekers may harm themselves or even suicide [151]. Therefore, many works focus on mental health and empathetic dialogue [3,37,54,76,111,125,138]. However, there is still a large gap between current dialogue models and human professionals [138].…”

Section: Risk Of Misleading and Privacy Informationmentioning

confidence: 99%

See 1 more Smart Citation

Recent Advances towards Safe, Responsible, and Moral Dialogue Systems: A Survey

Deng¹,

Sun²,

Zhang³

et al. 2023

Preprint

View full text Add to dashboard Cite

With the development of artificial intelligence, dialogue systems have been endowed with amazing chitchat capabilities, and there is widespread interest and discussion about whether the generated contents are socially beneficial. In this paper, we present a new perspective of research scope towards building a safe, responsible, and modal dialogue system, including 1) abusive and toxic contents, 2) unfairness and discrimination, 3) ethics and morality issues, and 4) risk of misleading and privacy information. Besides, we review the mainstream methods for evaluating the safety of large models from the perspectives of exposure and detection of safety issues. The recent advances in methodologies for the safety improvement of both end-to-end dialogue systems and pipeline-based models are further introduced. Finally, we discussed six existing challenges towards responsible AI: explainable safety monitoring, continuous learning of safety issues, robustness against malicious attacks, multimodal information processing, unified research framework, and multidisciplinary theory integration. We hope this survey will inspire further research toward safer dialogue systems. 1

show abstract

Section: Risk Of Misleading and Privacy Informationmentioning

confidence: 99%

“…Therefore, many works focus on mental health and empathetic dialogue [3,37,54,76,111,125,138]. However, there is still a large gap between current dialogue models and human professionals [138]. Also, users may ask for suggestions in professional areas such as law and medicine.…”

Section: Risk Of Misleading and Privacy Informationmentioning

confidence: 99%

Recent Advances towards Safe, Responsible, and Moral Dialogue Systems: A Survey

Deng¹,

Sun²,

Zhang³

et al. 2023

Preprint

View full text Add to dashboard Cite

show abstract

“…Rather than the data-driven paradigm, previous research finds that incorporating empathydemanded semantic information significantly improves empathy capability and the controllability of how to express empathy. Such semantic information ranges from the low-level emotions or dialogue acts to the high-level support strategies Sun et al, 2021a). Even commonsense knowledge can be utilized to improve the cognitive understanding of the users' mental states and experiences (Sabour et al, 2022).…”

Section: Failure Cases and Model Extensionsmentioning

confidence: 99%

EVA2.0: Investigating Open-Domain Chinese Dialogue Systems with Large-Scale Pre-Training

Gu¹,

Wen²,

Sun³

et al. 2022

Preprint

Self Cite

View full text Add to dashboard Cite

Large-scale pre-training has shown remarkable performance in building open-domain dialogue systems. However, previous works mainly focus on showing and evaluating the conversational performance of the released dialogue model, ignoring the discussion of some key factors towards a powerful human-like chatbot, especially in Chinese scenarios. In this paper, we conduct extensive experiments to investigate these under-explored factors, including data quality control, model architecture designs, training approaches, and decoding strategies. We propose EVA2.0, a largescale pre-trained open-domain Chinese dialogue model with 2.8 billion parameters, and make our models and code publicly available. To our knowledge, EVA2.0 is the largest opensource Chinese dialogue model. Automatic and human evaluations show that our model significantly outperforms other open-source counterparts. We also discuss the limitations of this work by presenting some failure cases and pose some future directions. 1

show abstract

“…In the past years, empathetic response generation has attracted much research interest (Rashkin et al, 2019;Majumder et al, 2020;Zandie and Mahoor, 2020;Sun et al, 2021). Rashkin et al (2019) suggest that dialog models can generate more empathetic responses by recognizing the interlocutor's emotion.…”

Section: Empathetic Response Generationmentioning

confidence: 99%

CoMAE: A Multi-factor Hierarchical Framework for Empathetic Response Generation

Zheng

Liu²,

Chen³

et al. 2021

Preprint

Self Cite

View full text Add to dashboard Cite

The capacity of empathy is crucial to the success of open-domain dialog systems. Due to its nature of multi-dimensionality, there are various factors that relate to empathy expression, such as communication mechanism, dialog act and emotion. However, existing methods for empathetic response generation usually either consider only one empathy factor or ignore the hierarchical relationships between different factors, leading to a weak ability of empathy modeling. In this paper, we propose a multi-factor hierarchical framework, CoMAE, for empathetic response generation, which models the above three key factors of empathy expression in a hierarchical way. We show experimentally that our CoMAEbased model can generate more empathetic responses than previous methods. We also highlight the importance of hierarchical modeling of different factors through both the empirical analysis on a real-life corpus and the extensive experiments. Our codes and used data are available at https://github.com/ chujiezheng/CoMAE.

show abstract

PsyQA: A Chinese Dataset for Generating Long Counseling Text for Mental Health Support

Cited by 24 publications

References 26 publications

Recent Advances towards Safe, Responsible, and Moral Dialogue Systems: A Survey

Recent Advances towards Safe, Responsible, and Moral Dialogue Systems: A Survey

EVA2.0: Investigating Open-Domain Chinese Dialogue Systems with Large-Scale Pre-Training

CoMAE: A Multi-factor Hierarchical Framework for Empathetic Response Generation

Contact Info

Product

Resources

About