Abstract
Machine reading comprehension (MRC), which requires a machine to answer questions based on a given context, has attracted increasing attention with the incorporation of various deep-learning techniques over the past few years. Although research on MRC based on deep learning is flourishing, there remains a lack of a comprehensive survey summarizing existing approaches and recent trends, which motivated the work presented in this article. Specifically, we give a thorough review of this research field, covering different aspects including (1) typical MRC tasks: their definitions, differences, and representative datasets; (2) the general architecture of neural MRC: the main modules and prevalent approaches to each; and (3) new trends: some emerging areas in neural MRC as well as the corresponding challenges. Finally, considering what has been achieved so far, the survey also envisages what the future may hold by discussing the open issues left to be addressed.
Highlights
Machine reading comprehension (MRC) is a task introduced to test the degree to which a machine can understand natural languages by asking the machine to answer questions based on a given context, which has the potential to revolutionize the way in which humans and machines interact with each other
Evaluation: Evaluation is a necessary part of MRC tasks
We introduce several representative datasets of each MRC task, highlighting how to construct large-scale datasets according to task requirements, and how to reduce lexical overlap between questions and context
Summary
Machine reading comprehension (MRC) is a task introduced to test the degree to which a machine can understand natural languages by asking the machine to answer questions based on a given context, which has the potential to revolutionize the way in which humans and machines interact with each other. As shown, a search engine with MRC techniques can directly return the correct answers to questions posed by users in natural language rather than a series of related web pages. Smart assistants equipped with an MRC system can read help documents and provide users with high-quality consulting services. MRC is a promising task, which can make information retrieval more efficient. MRC systems date back to the 1970s, the most notable of which was the QUALM system proposed by Lehnert [1]. In 1999, Hirschman et al [2]
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Free) 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
