机器阅读理解的研究进展

Survey on Machine Reading Comprehension

为便于厘清机器阅读理解任务的研究现状,按照答案来源,将机器阅读理解分为完形填空、片段选择、多项选择和答案生成4类.在统一的编码器—交互与推理—输出框架下对此4类任务的已有研究进行了综述,并描述了2种对此框架的可能扩展;最后讨论了机器阅读理解未来需要解决的问题.

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.