CGF: Constrained Generation Framework for Query Rewriting in Conversational AI

Jie Hao, Yang Liu, Xing Fan, Saurabh Gupta, Saleh Soltan, Rakesh Chada, Pradeep Natarajan, Chenlei Guo, Gokhan Tur

Abstract
In conversational AI agents, Query Rewriting (QR) plays a crucial role in reducing user frictions and satisfying their daily demands. User frictions are caused by various reasons, such as errors in the conversational AI system, users’ accent or their abridged language. In this work, we present a novel Constrained Generation Framework (CGF) for query rewriting at both global and personalized levels. It is based on the encoder-decoder framework, where the encoder takes the query and its previous dialogue turns as the input to form a context-enhanced representation, and the decoder uses constrained decoding to generate the rewrites based on the pre-defined global or personalized constrained decoding space. Extensive offline and online A/B experiments show that the proposed CGF significantly boosts the query rewriting performance.
Anthology ID:
2022.emnlp-industry.48
Volume:
Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing: Industry Track
Month:
December
Year:
2022
Address:
Abu Dhabi, UAE
Editors:
Yunyao Li, Angeliki Lazaridou
Venue:
EMNLP
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
475–483
Language:
URL:
https://aclanthology.org/2022.emnlp-industry.48
DOI:
10.18653/v1/2022.emnlp-industry.48
Bibkey:
Cite (ACL):
Jie Hao, Yang Liu, Xing Fan, Saurabh Gupta, Saleh Soltan, Rakesh Chada, Pradeep Natarajan, Chenlei Guo, and Gokhan Tur. 2022. CGF: Constrained Generation Framework for Query Rewriting in Conversational AI. In Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing: Industry Track, pages 475–483, Abu Dhabi, UAE. Association for Computational Linguistics.
Cite (Informal):
CGF: Constrained Generation Framework for Query Rewriting in Conversational AI (Hao et al., EMNLP 2022)
Copy Citation:
PDF:
https://preview.aclanthology.org/nschneid-patch-5/2022.emnlp-industry.48.pdf
PDF Search