DialogUSR: Complex Dialogue Utterance Splitting and Reformulation for Multiple Intent Detection
Haoran Meng, Zheng Xin, Tianyu Liu, Zizhen Wang, He Feng, Binghuai Lin, Xuemin Zhao, Yunbo Cao
Abstract
While interacting with chatbots, users may elicit multiple intents in a single dialogue utterance. Instead of training a dedicated multi-intent detection model, we propose DialogUSR, a dialogue utterance splitting and reformulation task that first splits multi-intent user query into several single-intent sub-queries and then recovers all the coreferred and omitted information in the sub-queries. DialogUSR can serve as a plug-in and domain-agnostic module that empowers the multi-intent detection for the deployed chatbots with minimal efforts. We collect a high-quality naturally occurring dataset that covers 23 domains with a multi-step crowd-souring procedure. To benchmark the proposed dataset, we propose multiple action-based generative models that involve end-to-end and two-stage training, and conduct in-depth analyses on the pros and cons of the proposed baselines.
BibTeX
@inproceedings{meng-etal-2022-dialogusr,
title = "{D}ialog{USR}: Complex Dialogue Utterance Splitting and Reformulation for Multiple Intent Detection",
author = "Meng, Haoran and
Xin, Zheng and
Liu, Tianyu and
Wang, Zizhen and
Feng, He and
Lin, Binghuai and
Zhao, Xuemin and
Cao, Yunbo and
Sui, Zhifang",
editor = "Goldberg, Yoav and
Kozareva, Zornitsa and
Zhang, Yue",
booktitle = "Findings of the Association for Computational Linguistics: EMNLP 2022",
month = dec,
year = "2022",
address = "Abu Dhabi, United Arab Emirates",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2022.findings-emnlp.234/",
doi = "10.18653/v1/2022.findings-emnlp.234",
pages = "3214--3229"
}