Abstract
Smart Reply (SR) systems present a user with a set of replies, of which one can be selected in place of having to type out a response. To perform well at this task, a system should be able to effectively present the user with a diverse set of options, to maximise the chance that at least one of them conveys the user’s desired response. This is a significant challenge, due to the lack of datasets containing sets of responses to learn from. Resultantly, previous work has focused largely on post-hoc diversification, rather than explicitly learning to predict sets of responses. Motivated by this problem, we present a novel method SimSR, that employs model-based simulation to discover high-value response sets, through simulating possible user responses with a learned world model. Unlike previous approaches, this allows our method to directly optimise the end-goal of SR–maximising the relevance of at least one of the predicted replies. Empirically on two public datasets, when compared to SoTA baselines, our method achieves up to 21% and 18% improvement in ROUGE score and Self-ROUGE score respectively.- Anthology ID:
- 2023.acl-long.672
- Volume:
- Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)
- Month:
- July
- Year:
- 2023
- Address:
- Toronto, Canada
- Editors:
- Anna Rogers, Jordan Boyd-Graber, Naoaki Okazaki
- Venue:
- ACL
- SIG:
- Publisher:
- Association for Computational Linguistics
- Note:
- Pages:
- 12030–12043
- Language:
- URL:
- https://aclanthology.org/2023.acl-long.672
- DOI:
- 10.18653/v1/2023.acl-long.672
- Cite (ACL):
- Benjamin Towle and Ke Zhou. 2023. Model-Based Simulation for Optimising Smart Reply. In Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 12030–12043, Toronto, Canada. Association for Computational Linguistics.
- Cite (Informal):
- Model-Based Simulation for Optimising Smart Reply (Towle & Zhou, ACL 2023)
- PDF:
- https://preview.aclanthology.org/nschneid-patch-5/2023.acl-long.672.pdf