Convolutional Spatial Attention Model for Reading Comprehension with Multiple-Choice Questions

Authors

  • Zhipeng Chen iFLYTEK Research
  • Yiming Cui iFLYTEK Research
  • Wentao Ma iFLYTEK Research
  • Shijin Wang iFLYTEK Research
  • Guoping Hu iFLYTEK Research

DOI:

https://doi.org/10.1609/aaai.v33i01.33016276

Abstract

Machine Reading Comprehension (MRC) with multiplechoice questions requires the machine to read given passage and select the correct answer among several candidates. In this paper, we propose a novel approach called Convolutional Spatial Attention (CSA) model which can better handle the MRC with multiple-choice questions. The proposed model could fully extract the mutual information among the passage, question, and the candidates, to form the enriched representations. Furthermore, to merge various attention results, we propose to use convolutional operation to dynamically summarize the attention values within the different size of regions. Experimental results show that the proposed model could give substantial improvements over various state-of- the-art systems on both RACE and SemEval-2018 Task11 datasets.

Downloads

Published

2019-07-17

How to Cite

Chen, Z., Cui, Y., Ma, W., Wang, S., & Hu, G. (2019). Convolutional Spatial Attention Model for Reading Comprehension with Multiple-Choice Questions. Proceedings of the AAAI Conference on Artificial Intelligence, 33(01), 6276-6283. https://doi.org/10.1609/aaai.v33i01.33016276

Issue

Section

AAAI Technical Track: Natural Language Processing