机器阅读理解综述  

A Review of Machine Reading Comprehension

作　　者：殷明[1] 

机构地区：[1]公安部第一研究所,北京

出　　处：《计算机科学与应用》2020年第12期2457-2465,共9页Computer Science and Application

摘　　要：机器阅读理解是为了让机器能够真正理解人类语言,它是人工智能发展过程中不可或缺的步骤。由于自然语言的复杂性和多样性导致全面理解自然语言是智能化领域的难点问题之一。本文介绍了机器阅读理解相关的技术方法,主要分为基于规则的方法、基于机器学习的方法和基于深度学习的方法,并分类对机器阅读理解领域的相关代表性工作进行了详细的总结。随着深度学习在多个领域取得成果能够,本文重点介绍了基于深度学习的机器阅读理解方法。最后本文对机器阅读理解未来发展趋势进行展望。Machine reading comprehension is to make the machine truly understand human language. Machine reading comprehension is an indispensable step in the development of artificial intelligence. Due to the complexity and diversity of the natural language, comprehensive understanding of the language is one of the difficult problems in the field of the intelligence. This paper introduces the related technologies and methods of machine reading comprehension, which are mainly divided into rule-based, machine learning-based and deep learning-based. We summarize the relevant representative work in detail. With the achievements of deep learning in many fields, this paper focuses on the machine reading comprehension method based on deep learning. Finally, the future development trend of machine reading comprehension is prospected.

关 键 词：机器阅读理解 深度学习 词向量 自然语言处理 

分 类 号：G63[文化科学—教育学]