StackReader: An RNN-Free Reading Comprehension Model

Authors

  • Yibo Jiang Columbia University
  • Zhou Zhao Zhejiang University

Keywords:

Reading Comprehension, Natural Language Processing, Attention

Abstract

Machine comprehension of text is the problem to answer a query based on a given context. Many existing systems use RNN-based units for contextual modeling linked with some attention mechanisms. In this paper, however, we propose StackReader, an end-to-end neural network model, to solve this problem, without recurrent neural network (RNN) units and its variants. This simple model is based solely on attention mechanism and gated convolutional neural network. Experiments on SQuAD have shown to have relatively high accuracy with a significant decrease in training time.

Downloads

Published

2018-04-29

How to Cite

Jiang, Y., & Zhao, Z. (2018). StackReader: An RNN-Free Reading Comprehension Model. Proceedings of the AAAI Conference on Artificial Intelligence, 32(1). Retrieved from https://ojs.aaai.org/index.php/AAAI/article/view/12169