Abstract
Machine Reading Comprehension (MRC) is an essential task in natural language understanding in which the goal is to teach machines to understand the text. Machine understanding can be evaluated through question answering techniques. Limited research has been done in Arabic reading comprehension. This study presents a survey on trends and methods of Machine Reading Comprehension (MRC) methods in Arabic. The survey summarizes recent advances in Arabic reading comprehension, primarily emphasizing on two aspects (i.e., available datasets and methods). The study provides a detailed analysis of MRC techniques and compares various datasets used to study Arabic reading compression.