We propose a novel neural attention architecture to tackle machine comprehension tasks, such as answering Cloze-style queries with respect to a document. Unlike previous models, we do not collapse the query into a single vector, instead we deploy an iterative alternating attention mechanism that allows a fine-grained exploration of both the query and the document. Our model outperforms state-of-the-art baselines in standard machine comprehension benchmarks such as CNN news articles and the Children's Book Test (CBT) dataset.
@article{arxiv.1606.02245,
title = {Iterative Alternating Neural Attention for Machine Reading},
author = {Alessandro Sordoni and Philip Bachman and Adam Trischler and Yoshua Bengio},
journal= {arXiv preprint arXiv:1606.02245},
year = {2016}
}