论文标题
几个以查询为重点的摘要，前缀合并
Few-shot Query-Focused Summarization with Prefix-Merging
论文作者
论文摘要
以查询为重点的摘要被认为是文本摘要的重要扩展。它旨在为给定查询生成简洁的亮点。与文本摘要不同，以查询为重点的摘要长期以来一直困扰着缺乏高质量的大规模数据集的问题。在本文中，我们调查了我们是否可以整合和转移文本摘要的知识和问题回答以协助以查询为重点的摘要中的少数学习的想法。在这里，我们提出了前缀 - 合并，这是一种基于以查询为重点的摘要中几个弹药学习的前缀预验证策略。从前缀调整中汲取灵感，我们可以从文本摘要中整合任务知识，并将回答的问题整合到正确设计的前缀中，并将合并的前缀应用于以查询为中心的摘要。只有少量可训练的参数，对以查询为重点的摘要的前缀合并优于微调。我们进一步讨论了不同前缀设计的影响，并为前缀合并的工作方式提供了可视化的解释。
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.
