Leveraging Slot Descriptions for Zero-Shot Cross-Domain Dialogue StateTracking
Zhaojiang Lin, Bing Liu, Seungwhan Moon, Paul Crook, Zhenpeng Zhou, Zhiguang Wang, Zhou Yu, Andrea Madotto
Abstract
Zero-shot cross-domain dialogue state tracking (DST) enables us to handle unseen domains without the expense of collecting in-domain data. In this paper, we propose a slot descriptions enhanced generative approach for zero-shot cross-domain DST. Specifically, our model first encodes a dialogue context and a slot with a pre-trained self-attentive encoder, and generates slot value in auto-regressive manner. In addition, we incorporate Slot Type Informed Descriptions that capture the shared information of different slots to facilitates the cross-domain knowledge transfer. Experimental results on MultiWOZ shows that our model significantly improve existing state-of-the-art results in zero-shot cross-domain setting.
BibTeX
@inproceedings{lin-etal-2021-leveraging,
title = "Leveraging Slot Descriptions for Zero-Shot Cross-Domain Dialogue {S}tate{T}racking",
author = "Lin, Zhaojiang and
Liu, Bing and
Moon, Seungwhan and
Crook, Paul and
Zhou, Zhenpeng and
Wang, Zhiguang and
Yu, Zhou and
Madotto, Andrea and
Cho, Eunjoon and
Subba, Rajen",
editor = "Toutanova, Kristina and
Rumshisky, Anna and
Zettlemoyer, Luke and
Hakkani-Tur, Dilek and
Beltagy, Iz and
Bethard, Steven and
Cotterell, Ryan and
Chakraborty, Tanmoy and
Zhou, Yichao",
booktitle = "Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies",
month = jun,
year = "2021",
address = "Online",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2021.naacl-main.448/",
doi = "10.18653/v1/2021.naacl-main.448",
pages = "5640--5648"
}