MemSum-DQA：将高效长文档抽取式摘要器用于文档问答
计算与语言
2023-10-11 v1
摘要
我们介绍了 MemSum-DQA，一种利用长文档抽取式摘要器 MemSum 的文档问答（DQA）高效系统。通过将解析文档中每个文本块前缀以所给问题及问题类型，MemSum-DQA 从文档中有选择地抽取文本块作为答案。在全文档问答任务上，该方法相较先前最优基线在精确匹配准确率上提升 9%。值得注意的是，MemSum-DQA 在涉及子关系理解的问题上表现突出，彰显了抽取式摘要技术用于 DQA 任务的潜力。
引用
@article{arxiv.2310.06436,
title = {MemSum-DQA: Adapting An Efficient Long Document Extractive Summarizer for Document Question Answering},
author = {Nianlong Gu and Yingqiang Gao and Richard H. R. Hahnloser},
journal= {arXiv preprint arXiv:2310.06436},
year = {2023}
}
备注
This paper is the technical research paper of CIKM 2023 DocIU challenges. The authors received the CIKM 2023 DocIU Winner Award, sponsored by Google, Microsoft, and the Centre for data-driven geoscience