English

Iterative Alternating Neural Attention for Machine Reading

Computation and Language 2016-11-10 v4 Neural and Evolutionary Computing

Abstract

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.

Keywords

Cite

@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}
}
R2 v1 2026-06-22T14:19:47.517Z