Multi-Matching Network for Multiple Choice Reading Comprehension

Authors

  • Min Tang Sun Yat-sen University
  • Jiaran Cai Sun Yat-sen University
  • Hankz Hankui Zhuo Sun Yat-sen University

DOI:

https://doi.org/10.1609/aaai.v33i01.33017088

Abstract

Multiple-choice machine reading comprehension is an important and challenging task where the machine is required to select the correct answer from a set of candidate answers given passage and question. Existing approaches either match extracted evidence with candidate answers shallowly or model passage, question and candidate answers with a single paradigm of matching. In this paper, we propose Multi-Matching Network (MMN) which models the semantic relationship among passage, question and candidate answers from multiple different paradigms of matching. In our MMN model, each paradigm is inspired by how human think and designed under a unified compose-match framework. To demonstrate the effectiveness of our model, we evaluate MMN on a large-scale multiple choice machine reading comprehension dataset (i.e. RACE). Empirical results show that our proposed model achieves a significant improvement compared to strong baselines and obtains state-of-the-art results.

Downloads

Published

2019-07-17

How to Cite

Tang, M., Cai, J., & Zhuo, H. H. (2019). Multi-Matching Network for Multiple Choice Reading Comprehension. Proceedings of the AAAI Conference on Artificial Intelligence, 33(01), 7088-7095. https://doi.org/10.1609/aaai.v33i01.33017088

Issue

Section

AAAI Technical Track: Natural Language Processing