TY - JOUR AU - Jiang, Yibo AU - Zhao, Zhou PY - 2018/04/29 Y2 - 2024/03/28 TI - StackReader: An RNN-Free Reading Comprehension Model JF - Proceedings of the AAAI Conference on Artificial Intelligence JA - AAAI VL - 32 IS - 1 SE - Student Abstract Track DO - 10.1609/aaai.v32i1.12169 UR - https://ojs.aaai.org/index.php/AAAI/article/view/12169 SP - AB - <p> 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. </p> ER -