A Scalable Framework for Learning From Implicit User Feedback to Improve Natural Language Understanding in Large-Scale Conversational AI Systems
Sunghyun Park, Han Li, Ameen Patel, Sidharth Mudgal, Sungjin Lee, Young-Bum Kim, Spyros Matsoukas, Ruhi Sarikaya
Abstract
Natural Language Understanding (NLU) is an established component within a conversational AI or digital assistant system, and it is responsible for producing semantic understanding of a user request. We propose a scalable and automatic approach for improving NLU in a large-scale conversational AI system by leveraging implicit user feedback, with an insight that user interaction data and dialog context have rich information embedded from which user satisfaction and intention can be inferred. In particular, we propose a domain-agnostic framework for curating new supervision data for improving NLU from live production traffic. With an extensive set of experiments, we show the results of applying the framework and improving NLU for a large-scale production system across 10 domains.
BibTeX
@inproceedings{park-etal-2021-scalable,
title = "A Scalable Framework for Learning From Implicit User Feedback to Improve Natural Language Understanding in Large-Scale Conversational {AI} Systems",
author = "Park, Sunghyun and
Li, Han and
Patel, Ameen and
Mudgal, Sidharth and
Lee, Sungjin and
Kim, Young-Bum and
Matsoukas, Spyros and
Sarikaya, Ruhi",
editor = "Moens, Marie-Francine and
Huang, Xuanjing and
Specia, Lucia and
Yih, Scott Wen-tau",
booktitle = "Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing",
month = nov,
year = "2021",
address = "Online and Punta Cana, Dominican Republic",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2021.emnlp-main.489/",
doi = "10.18653/v1/2021.emnlp-main.489",
pages = "6054--6063"
}