Model-Based Simulation for Optimising Smart Reply

Benjamin Towle, Ke Zhou


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
Bibkey:
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)
Copy Citation:
PDF:
https://aclanthology.org/2023.acl-long.672.pdf
Video:
 https://aclanthology.org/2023.acl-long.672.mp4