Domain-Oriented Prefix-Tuning: Towards Efficient and Generalizable Fine-tuning for Zero-Shot Dialogue Summarization
Lulu Zhao, Fujia Zheng, Weihao Zeng, Keqing He, Weiran Xu, Huixing Jiang, Wei Wu, Yanan Wu
Abstract
The most advanced abstractive dialogue summarizers lack generalization ability on new domains and the existing researches for domain adaptation in summarization generally rely on large-scale pre-trainings. To explore the lightweight fine-tuning methods for domain adaptation of dialogue summarization, in this paper, we propose an efficient and generalizable Domain-Oriented Prefix-tuning model, which utilizes a domain word initialized prefix module to alleviate domain entanglement and adopts discrete prompts to guide the model to focus on key contents of dialogues and enhance model generalization. We conduct zero-shot experiments and build domain adaptation benchmarks on two multi-domain dialogue summarization datasets, TODSum and QMSum. Adequate experiments and qualitative analysis prove the effectiveness of our methods.
BibTeX
@inproceedings{zhao-etal-2022-domain,
title = "Domain-Oriented Prefix-Tuning: Towards Efficient and Generalizable Fine-tuning for Zero-Shot Dialogue Summarization",
author = "Zhao, Lulu and
Zheng, Fujia and
Zeng, Weihao and
He, Keqing and
Xu, Weiran and
Jiang, Huixing and
Wu, Wei and
Wu, Yanan",
editor = "Carpuat, Marine and
de Marneffe, Marie-Catherine and
Meza Ruiz, Ivan Vladimir",
booktitle = "Proceedings of the 2022 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies",
month = jul,
year = "2022",
address = "Seattle, United States",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2022.naacl-main.357/",
doi = "10.18653/v1/2022.naacl-main.357",
pages = "4848--4862"
}