“Iterative Alternating Neural Attention for Machine Reading”, Alessandro Sordoni, Philip Bachman, Adam Trischler, Yoshua Bengio2016-06-07 (RNN, self-attention; backlinks; similar)⁠:

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.

Backlinks:

Similar Links: