Papers › Iterative Alternating Neural Attention for Machine Reading

Iterative Alternating Neural Attention for Machine Reading

7 Jun 2016arXiv:1606.02245archive 2025-07-28

Alessandro Sordoni, Philip Bachman, Adam Trischler, Yoshua Bengio

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.

PaperPDFCode

Code

AI-metrics/AI-metrics mentioned on GitHubNOASSERTION report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

Not run by Syntology. Nothing on this page verifies that the listed code works.

Tasks

ArticlesQuestion AnsweringReading Comprehension

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Question Answering CNN / Daily Mail AIA CNN 76.1 #5 of 16 Archive leaderboard report
Question Answering Children's Book Test AIA Accuracy-NE 72% #8 of 8 Archive leaderboard report

Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections