Exploiting domain-slot related keywords description for Few-Shot Cross-Domain Dialogue State Tracking
Gao Qixiang, Guanting Dong, Yutao Mou, Liwen Wang, Chen Zeng, Daichi Guo, Mingyang Sun, Weiran Xu
Abstract
Collecting dialogue data with domain-slot-value labels for dialogue state tracking (DST) could be a costly process. In this paper, we propose a novel framework based on domain-slot related description to tackle the challenge of few-shot cross-domain DST. Specifically, we design an extraction module to extract domain-slot related verbs and nouns in the dialogue. Then, we integrates them into the description, which aims to prompt the model to identify the slot information. Furthermore, we introduce a random sampling strategy to improve the domain generalization ability of the model. We utilize a pre-trained model to encode contexts and description and generates answers with an auto-regressive manner. Experimental results show that our approaches substantially outperform the existing few-shot DST methods on MultiWOZ and gain strong improvements on the slot accuracy comparing to existing slot description methods.
BibTeX
@inproceedings{qixiang-etal-2022-exploiting,
title = "Exploiting domain-slot related keywords description for Few-Shot Cross-Domain Dialogue State Tracking",
author = "Qixiang, Gao and
Dong, Guanting and
Mou, Yutao and
Wang, Liwen and
Zeng, Chen and
Guo, Daichi and
Sun, Mingyang and
Xu, Weiran",
editor = "Goldberg, Yoav and
Kozareva, Zornitsa and
Zhang, Yue",
booktitle = "Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing",
month = dec,
year = "2022",
address = "Abu Dhabi, United Arab Emirates",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2022.emnlp-main.157/",
doi = "10.18653/v1/2022.emnlp-main.157",
pages = "2460--2465"
}