Personalized Dense Retrieval on Global Index for Voice-enabled Conversational Systems

Masha Belyi, Charlotte Dzialo, Chaitanya Dwivedi, Prajit Muppidi, Kanna Shimizu


Abstract
Voice-controlled AI dialogue systems are susceptible to noise from phonetic variations and failure to resolve ambiguous entities. Typically, personalized entity resolution (ER) and/or query rewrites (QR) are deployed to recover from these error modes. Previous work in this field achieves personalization by constraining retrieval search space to personalized indices built from user’s historical interactions with the device. While constrained retrieval achieves high precision, predictions are limited to entities in recent user history, which offers low coverage of future requests. Further, maintaining individual indices for millions of users is memory intensive and difficult to scale. In this work, we propose a personalized entity retrieval system that is robust to phonetic noise and ambiguity but is not limited to a personalized index. We achieve this by embedding user listening preferences into a contextual query embedding used in retrieval. We demonstrate our model’s ability to correct multiple error modes and show 91% improvement over baseline on the entity retrieval task. Finally, we optimize the end-to-end approach to fit within online latency constraints while maintaining gains in performance.
Anthology ID:
2023.emnlp-industry.9
Volume:
Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing: Industry Track
Month:
December
Year:
2023
Address:
Singapore
Editors:
Mingxuan Wang, Imed Zitouni
Venue:
EMNLP
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
83–92
Language:
URL:
https://aclanthology.org/2023.emnlp-industry.9
DOI:
10.18653/v1/2023.emnlp-industry.9
Bibkey:
Cite (ACL):
Masha Belyi, Charlotte Dzialo, Chaitanya Dwivedi, Prajit Muppidi, and Kanna Shimizu. 2023. Personalized Dense Retrieval on Global Index for Voice-enabled Conversational Systems. In Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing: Industry Track, pages 83–92, Singapore. Association for Computational Linguistics.
Cite (Informal):
Personalized Dense Retrieval on Global Index for Voice-enabled Conversational Systems (Belyi et al., EMNLP 2023)
Copy Citation:
PDF:
https://aclanthology.org/2023.emnlp-industry.9.pdf
Video:
 https://aclanthology.org/2023.emnlp-industry.9.mp4