A Comprehensive Survey on Multi-hop Machine Reading Comprehension Datasets and Metrics
نویسندگان
1 Computer Engineering Faculty,University of Isfahan, Isfahan, Iran.
2 Computer Engineering Faculty,University of Isfahan, Isfahan, Iran.
doi
10.22108/jcs.2025.143323.1153چکیده
Multi-hop Machine reading comprehension is a challenge field in natural language processing and its goal is to find the answer of questions based on disjoint pieces of information in a natural language context. Due to the complexity and importance of this field, a large number of studies have been focused on multi-hop MRC recently. Then it is necessary and worth reviewing them in detail. Since datasets and evaluation metrics play a crucial role in the progress of research in this field, this study aims to present a comprehensive survey on recent advances in multi-hop MRC evaluation metrics and datasets. In this regard, the existing multi-hop MRC evaluation metrics and datasets are reviewed from 2017 to 2025, and a comprehensive analysis has been prepared at the end and. Also, open issues in this field have been discussed.