Iterative Alternating Neural Attention for Machine Reading
This work addresses the problem of improving machine reading comprehension for AI systems, representing an incremental advancement with a novel method for a known bottleneck.
The paper tackles machine comprehension tasks by proposing a novel neural attention architecture that uses iterative alternating attention for fine-grained exploration of queries and documents, achieving state-of-the-art performance on benchmarks like CNN news articles and the Children's Book Test.
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.