Iterative Alternating Neural Attention For Machine Reading

Alessandro Sordoni, Philip Bachman, Adam Trischler, Yoshua Bengio . Arxiv 2016 – 40 citations

[Paper]    
Datasets Model Architecture

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.

Similar Work