BriefGPT.xyz
Dec, 2017
阅读理解的上下文化词表示
Contextualized Word Representations for Reading Comprehension
HTML
PDF
Shimi Salant, Jonathan Berant
TL;DR
论文研究了使用神经网络和预训练语言模型来提取文件中问题的答案，通过提供丰富的上下文表示并允许模型在上下文相关和上下文无关的单词表示之间进行选择，可以获得比现有技术更好的性能。
Abstract
Reading a
document
and extracting an answer to a question about its content has attracted substantial attention recently, where most work has focused on the interaction between the question and the
document
. In t
→