Zero-Shot Dialogue State Tracking via Cross-Task Transfer

Zhaojiang Lin, Bing Liu, Andrea Madotto, Seungwhan Moon, Zhenpeng Zhou, Paul Crook, Zhiguang Wang, Zhou Yu, Eunjoon Cho, Rajen Subba, Pascale Fung


Abstract
Zero-shot transfer learning for dialogue state tracking (DST) enables us to handle a variety of task-oriented dialogue domains without the expense of collecting in-domain data. In this work, we propose to transfer the cross-task knowledge from general question answering (QA) corpora for the zero-shot DST task. Specifically, we propose TransferQA, a transferable generative QA model that seamlessly combines extractive QA and multi-choice QA via a text-to-text transformer framework, and tracks both categorical slots and non-categorical slots in DST. In addition, we introduce two effective ways to construct unanswerable questions, namely, negative question sampling and context truncation, which enable our model to handle none value slots in the zero-shot DST setting. The extensive experiments show that our approaches substantially improve the existing zero-shot and few-shot results on MultiWoz. Moreover, compared to the fully trained baseline on the Schema-Guided Dialogue dataset, our approach shows better generalization ability in unseen domains.
Anthology ID:
2021.emnlp-main.622
Volume:
Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing
Month:
November
Year:
2021
Address:
Online and Punta Cana, Dominican Republic
Editors:
Marie-Francine Moens, Xuanjing Huang, Lucia Specia, Scott Wen-tau Yih
Venue:
EMNLP
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
7890–7900
Language:
URL:
https://aclanthology.org/2021.emnlp-main.622
DOI:
10.18653/v1/2021.emnlp-main.622
Bibkey:
Cite (ACL):
Zhaojiang Lin, Bing Liu, Andrea Madotto, Seungwhan Moon, Zhenpeng Zhou, Paul Crook, Zhiguang Wang, Zhou Yu, Eunjoon Cho, Rajen Subba, and Pascale Fung. 2021. Zero-Shot Dialogue State Tracking via Cross-Task Transfer. In Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing, pages 7890–7900, Online and Punta Cana, Dominican Republic. Association for Computational Linguistics.
Cite (Informal):
Zero-Shot Dialogue State Tracking via Cross-Task Transfer (Lin et al., EMNLP 2021)
Copy Citation:
PDF:
https://aclanthology.org/2021.emnlp-main.622.pdf
Video:
 https://aclanthology.org/2021.emnlp-main.622.mp4
Code
 facebookresearch/Zero-Shot-DST
Data
DREAMHotpotQAMRQANewsQARACESGDSQuADSearchQATriviaQA