Few-shot Query-Focused Summarization with Prefix-Merging
This work addresses a data scarcity problem for researchers and practitioners in NLP, offering an incremental improvement in few-shot learning for query-focused summarization.
The paper tackles the lack of large-scale datasets in query-focused summarization by proposing prefix-merging, a prefix-based pretraining strategy that integrates knowledge from text summarization and question answering, achieving better performance than fine-tuning with only a small number of trainable parameters.
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.