Affiliations: [a]
College of Computer Science and Engineering, North Minzu University, Yinchuan, China
| [b]
College of Mathematics and Information Science, North Minzu University, Yinchuan, China
Correspondence:
[*]
Corresponding author. Jinlin Ma, College of computer science and engineering, North Minzu University, Yinchuan, China. E-mail: [email protected].
Abstract: Text-based reading comprehension models have great research significance and market value and are one of the main directions of natural language processing. Reading comprehension models of single-span answers have recently attracted more attention and achieved significant results. In contrast, multi-span answer models for reading comprehension have been less investigated and their performances need improvement. To address this issue, in this paper, we propose a text-based multi-span network for reading comprehension, ALBERT_SBoundary, and build a multi-span answer corpus, MultiSpan_NMU. We also conduct extensive experiments on the public multi-span corpus, MultiSpan_DROP, and our multi-span answer corpus, MultiSpan_NMU, and compare the proposed method with the state-of-the-art. The experimental results show that our proposed method achieves F1 scores of 84.10 and 92.88 on MultiSpan_DROP and MultiSpan_NMU datasets, respectively, while it also has fewer parameters and a shorter training time.
Keywords: Multi-span answer, ALBERT model, reading comprehension, minimum order matching prediction algorithm
