To answer the question in machine comprehension (MC) task, the models need to establish the interaction between the question and the context. To tackle the problem that the single-pass model cannot reflect on and correct its answer, we present Ruminating Reader. Ruminating Reader adds a second pass of attention and a novel information fusion component to the Bi-Directional Attention Flow model (BiDAF). We propose novel layer structures that construct an query-aware context vector representation and fuse encoding representation with intermediate representation on top of BiDAF model. We show that a multi-hop attention mechanism can be applied to a bi-directional attention structure. In experiments on SQuAD, we find that the Reader outperforms the BiDAF baseline by a substantial margin, and matches or surpasses the performance of all other published systems.
@article{arxiv.1704.07415,
title = {Ruminating Reader: Reasoning with Gated Multi-Hop Attention},
author = {Yichen Gong and Samuel R. Bowman},
journal= {arXiv preprint arXiv:1704.07415},
year = {2017}
}