Title: QANet-based candidate answer rethink model for machine reading comprehension

Authors: Yong Wang; Chong Lei

Addresses: School of Artificial Intelligence, Liangjiang, Chongqing University of Technology, Banan, Chongqing 401135, China ' College of Computer Science and Engineering, Chongqing University of Technology, Banan, Chongqing 400054, China

Abstract: The current model applied to the span extraction reading comprehension task fuses the information of context and question, and outputs the index with the highest probability calculated in the context as the prediction span. In this process, the model discards all the remaining candidate answers, which results in a waste of the available information in the candidate answers. Our model is designed to simulate the behaviour of human beings choosing multiple candidate answers and comprehensively judging the final answer in reading comprehension tasks. We propose the QANet-based candidate answer rethink model. The model interacts and fuses multiple candidate answers with context and question, prompting the model to obtain a more accurate answer by synthesising these three aspects of information. Experiments show that our model has made new progress in performance.

Keywords: machine reading comprehension; candidate answer rethink; information interaction.

DOI: 10.1504/IJWMC.2021.115639

International Journal of Wireless and Mobile Computing, 2021 Vol.20 No.3, pp.246 - 254

Received: 20 Aug 2020
Accepted: 14 Sep 2020

Published online: 15 Jun 2021 *

Full-text access for editors Full-text access for subscribers Purchase this article Comment on this article