%0 Journal Article
%A BAI Zi-wei
%A LI Ke
%A YUAN Cai-xia
%A WANG Xiao-jie
%T Survey on Machine Reading Comprehension
%D 
%R 10.13190/j.jbupt.2019-111
%J Journal of Beijing University of Posts and Telecommunications
%P 1-9
%V 42
%N 6
%X In order to make clear the recent work of machine reading comprehension (MRC) tasks, they are divided into four types of subtasks with different sources of answers. They are cloze-style, span selection, multi-choice, and answer generation. Previous work on these four different types of subtasks is investigated under a unified framework of encoder-interaction and reasoning-output. Two types of recent developments for the frame are also given. Several challenges on MRC for future work are discussed at the end of the survey.
%U https://journal.bupt.edu.cn/EN/10.13190/j.jbupt.2019-111