A Survey on Machine Reading Comprehension Systems

被引:28
作者
Baradaran, Razieh [1 ]
Ghiasi, Razieh [1 ]
Amirkhani, Hossein [1 ]
机构
[1] Univ Qom, Comp & Informat Technol Dept, Qom, Iran
关键词
Natural Language Processing; question answering; Machine Reading Comprehension; deep learning; literature review; QUESTION ANSWERING SYSTEMS; NETWORK; MODEL;
D O I
10.1017/S1351324921000395
中图分类号
TP18 [人工智能理论];
学科分类号
081104 ; 0812 ; 0835 ; 1405 ;
摘要
Machine Reading Comprehension (MRC) is a challenging task and hot topic in Natural Language Processing. The goal of this field is to develop systems for answering the questions regarding a given context. In this paper, we present a comprehensive survey on diverse aspects of MRC systems, including their approaches, structures, input/outputs, and research novelties. We illustrate the recent trends in this field based on a review of 241 papers published during 2016-2020. Our investigation demonstrated that the focus of research has changed in recent years from answer extraction to answer generation, from single- to multi-document reading comprehension, and from learning from scratch to using pre-trained word vectors. Moreover, we discuss the popular datasets and the evaluation metrics in this field. The paper ends with an investigation of the most-cited papers and their contributions.
引用
收藏
页码:683 / 732
页数:50
相关论文
共 282 条
[1]  
Aghaebrahimian Ahmad, 2018, CONLL, P433
[2]  
Akour Mohammed, 2011, American Journal of Applied Sciences, V8, P652, DOI 10.3844/ajassp.2011.652.661
[3]  
Amirkhani H., 2020, ARXIV PREPRINT ARXIV
[4]  
Andor D, 2019, 2019 CONFERENCE ON EMPIRICAL METHODS IN NATURAL LANGUAGE PROCESSING AND THE 9TH INTERNATIONAL JOINT CONFERENCE ON NATURAL LANGUAGE PROCESSING (EMNLP-IJCNLP 2019), P5947
[5]  
Angelidis Stefanos, 2019, P 2 WORKSHOP MACHINE, P78
[6]  
[Anonymous], 2018, Neural reading comprehension and beyond
[7]  
[Anonymous], 2018, QUESTION FOCUSED MUL
[8]  
[Anonymous], 2019, INT C LEARN REPR
[9]  
[Anonymous], 2016, IJCAI
[10]  
[Anonymous], 2017, ICLR