Few-shot Query-Focused Summarization with Prefix-Merging

Ruifeng Yuan, Zili Wang, Ziqiang Cao, Wenjie Li

Abstract
Query-focused summarization has been considered as an important extension for text summarization. It aims to generate a concise highlight for a given query. Different from text summarization, query-focused summarization has long been plagued by the problem of lacking high-quality large-scale datasets. In this paper, we investigate the idea that whether we can integrate and transfer the knowledge of text summarization and question answering to assist the few-shot learning in query-focused summarization. Here, we propose prefix-merging, a prefix-based pretraining strategy for few-shot learning in query-focused summarization. Drawn inspiration from prefix-tuning, we are allowed to integrate the task knowledge from text summarization and question answering into a properly designed prefix and apply the merged prefix to query-focused summarization. With only a small amount of trainable parameters, prefix-merging outperforms fine-tuning on query-focused summarization. We further discuss the influence of different prefix designs and propose a visualized explanation for how prefix-merging works.
Anthology ID:
2022.emnlp-main.243
Volume:
Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing
Month:
December
Year:
2022
Address:
Abu Dhabi, United Arab Emirates
Venue:
EMNLP
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
3704–3714
Language:
URL:
https://aclanthology.org/2022.emnlp-main.243
DOI:
10.18653/v1/2022.emnlp-main.243
Bibkey:
Cite (ACL):
Ruifeng Yuan, Zili Wang, Ziqiang Cao, and Wenjie Li. 2022. Few-shot Query-Focused Summarization with Prefix-Merging. In Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing, pages 3704–3714, Abu Dhabi, United Arab Emirates. Association for Computational Linguistics.
Cite (Informal):
Few-shot Query-Focused Summarization with Prefix-Merging (Yuan et al., EMNLP 2022)
Copy Citation:
PDF:
https://preview.aclanthology.org/remove-xml-comments/2022.emnlp-main.243.pdf
PDF Search