Publications
Detailed Information
Scalable and Safe Remediation of Defective Actions in Self-Learning Conversational Systems
Cited 0 time in
Web of Science
Cited 0 time in Scopus
- Authors
- Issue Date
- 2023-07
- Citation
- Association for Computational Linguistics (ACL). Annual Meeting Conference Proceedings, Vol.5, pp.361-367
- Abstract
- Off-Policy reinforcement learning has been a driving force for the state-of-the-art conversational AIs leading to more natural human-agent interactions and improving the user satisfaction for goal-oriented agents. However, in large-scale commercial settings, it is often challenging to balance between policy improvements and experience continuity on the broad spectrum of applications handled by such system. In the literature, off-policy evaluation and guard-railing on aggregate statistics has been commonly used to address this problem. In this paper, we propose a method for curating and leveraging high-precision samples sourced from historical regression incident reports to validate, safe-guard, and improve policies prior to the online deployment. We conducted extensive experiments using data from a real-world conversational system and actual regression incidents. The proposed method is currently deployed in our production system to protect customers against broken experiences and enable long-term policy improvements.
- ISSN
- 0736-587X
- Files in This Item:
- There are no files associated with this item.
Related Researcher
- College of Engineering
- Department of Electrical and Computer Engineering
Item View & Download Count
Items in S-Space are protected by copyright, with all rights reserved, unless otherwise indicated.