BriefGPT.xyz
Sep, 2020
生成式阅读理解的多跨度样式提取
Multi-span Style Extraction for Generative Reading Comprehension
HTML
PDF
Junjie Yang, Zhuosheng Zhang, Hai Zhao
TL;DR
该研究提出了一种多跨度抽取的框架，将单跨度抽取方法扩展到生成型MRC领域，旨在缓解生成型模型和单跨度模型之间的困境，并生成具有更好句法和语义形式的答案。
Abstract
generative machine reading comprehension
(
mrc
) requires a model to generate well-formed answers. For this type of
mrc
,
→