Summary of Stampsy: Towards Spatiotemporal-aware Mixed-type Dialogues For Psychological Counseling, by Jieyi Wang et al.
STAMPsy: Towards SpatioTemporal-Aware Mixed-Type Dialogues for Psychological Counseling
by Jieyi Wang, Yue Huang, Zeming Liu, Dexuan Xu, Chuan Wang, Xiaoming Shi, Ruiyuan Guan, Hongxing Wang, Weihua Yue, Yu Huang
First submitted to arxiv on: 21 Dec 2024
Categories
- Main: Artificial Intelligence (cs.AI)
- Secondary: None
GrooveSquid.com Paper Summaries
GrooveSquid.com’s goal is to make artificial intelligence research accessible by summarizing AI papers in simpler terms. Each summary below covers the same AI paper, written at different levels of difficulty. The medium difficulty and low difficulty versions are original summaries written by GrooveSquid.com, while the high difficulty version is the paper’s original abstract. Feel free to learn from the version that suits you best!
| Summary difficulty | Written by | Summary |
|---|---|---|
| High | Paper authors | High Difficulty Summary Read the original abstract here |
| Medium | GrooveSquid.com (original content) | Medium Difficulty Summary A novel approach to constructing mixed-type dialogue systems for online psychological counseling is proposed, addressing the challenge of enabling clients to clarify their goals before proceeding with counseling. The authors collect a corpus termed STAMPsy, comprising over 5,000 conversations across five dialogue types: task-oriented dialogue for diagnosis, knowledge-grounded dialogue, conversational recommendation, empathetic dialogue, and question answering. Additionally, spatiotemporal-aware knowledge is linked to dialogues in STAMPsy, allowing systems to have world awareness and affecting mental health. Baselines are built on STAMPsy, and an iterative self-feedback psychological dialogue generation framework, named Self-STAMPsy, is developed. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary Online counseling dialogue systems offer a convenient alternative to traditional therapy. Existing systems focus on basic empathetic dialogue or QA with minimal professional knowledge. This paper addresses the challenge of constructing mixed-type dialogue systems that enable clients to clarify their goals before counseling. A corpus called STAMPsy is collected, covering five dialogue types and over 5,000 conversations. The authors also link dialogues to spatiotemporal states and propose a dataset. Results show that clarifying dialogue goals in advance and utilizing spatiotemporal states are effective. |
Keywords
» Artificial intelligence » Question answering » Spatiotemporal
