Generative Zero-Shot Prompt Learning for Cross-Domain Slot Filling with Inverse Prompting
Xuefeng Li, Liwen Wang, Guanting Dong, Keqing He, Jinzheng Zhao, Hao Lei, Jiachi Liu, Weiran Xu
Abstract
Zero-shot cross-domain slot filling aims to transfer knowledge from the labeled source domain to the unlabeled target domain. Existing models either encode slot descriptions and examples or design handcrafted question templates using heuristic rules, suffering from poor generalization capability or robustness. In this paper, we propose a generative zero-shot prompt learning framework for cross-domain slot filling, both improving generalization and robustness than previous work. Besides, we introduce a novel inverse prompting strategy to distinguish different slot types to avoid the multiple prediction problem, and an efficient prompt tuning strategy to boost higher performance only training fewer prompt parameters. Experiments and analysis demonstrate the effectiveness of our proposed framework, especially huge improvements (+13.44% F1) on the unseen slots.
BibTeX
@inproceedings{li-etal-2023-generative,
title = "Generative Zero-Shot Prompt Learning for Cross-Domain Slot Filling with Inverse Prompting",
author = "Li, Xuefeng and
Wang, Liwen and
Dong, Guanting and
He, Keqing and
Zhao, Jinzheng and
Lei, Hao and
Liu, Jiachi and
Xu, Weiran",
editor = "Rogers, Anna and
Boyd-Graber, Jordan and
Okazaki, Naoaki",
booktitle = "Findings of the Association for Computational Linguistics: ACL 2023",
month = jul,
year = "2023",
address = "Toronto, Canada",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2023.findings-acl.52/",
doi = "10.18653/v1/2023.findings-acl.52",
pages = "825--834"
}