用检索增强多任务模型从长文档中提取最相关名言，性能提升5.08%。
RA-MTR: A Retrieval Augmented Multi-Task Reader based Approach for Inspirational Quote Extraction from Long Documents
- 先用向量库检索候选句，再用多任务阅读器精筛
- 在三个新数据集上实现最高5.08%的准确率提升
- 适合需要精准提取名人名言的研究与应用
名人名言常用于新闻、文章和日常对话中传递思想。本文提出一种基于上下文的名言提取系统，将该任务建模为开放域问答问题。首先利用基于向量存储的检索器筛选候选句，再通过多任务阅读器进行精确判断。我们构建了三个基于上下文的名言提取数据集，并提出新型多任务框架RA-MTR，显著提升当前最佳性能，在BoW F1-score上最大提升达5.08%。
原文摘要 · Abstract (English)
Inspirational quotes from famous individuals are often used to convey thoughts in news articles, essays, and everyday conversations. In this paper, we propose a novel context-based quote extraction system that aims to extract the most relevant quote from a long text. We formulate this quote extraction as an open domain question answering problem first by employing a vector-store based retriever and then applying a multi-task reader. We curate three context-based quote extraction datasets and introduce a novel multi-task framework RA-MTR that improves the state-of-the-art performance, achieving a maximum improvement of 5.08% in BoW F1-score.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。