Papers › Surprisingly Easy Hard-Attention for Sequence to Sequence Learning

Surprisingly Easy Hard-Attention for Sequence to Sequence Learning

1 Oct 2018EMNLP 2018 10archive 2025-07-28

Shiv Shankar, Siddhant Garg, Sunita Sarawagi

In this paper we show that a simple beam approximation of the joint distribution between attention and output is an easy, accurate, and efficient attention mechanism for sequence to sequence learning. The method combines the advantage of sharp focus in hard attention and the implementation ease of soft attention. On five translation tasks we show effortless and consistent gains in BLEU compared to existing attention mechanisms.

PaperPDFCode

Code

sid7954/beam-joint-attention officialmentioned in papertf 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

Hard AttentionImage CaptioningMorphological InflectionTranslation

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

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