Papers › Online and Linear-Time Attention by Enforcing Monotonic Alignments

Online and Linear-Time Attention by Enforcing Monotonic Alignments

3 Apr 2017ICML 2017 8arXiv:1704.00784archive 2025-07-28

Colin Raffel, Minh-Thang Luong, Peter J. Liu, Ron J. Weiss, Douglas Eck

Recurrent neural network models with an attention mechanism have proven to be extremely effective on a wide variety of sequence-to-sequence problems. However, the fact that soft attention mechanisms perform a pass over the entire input sequence when producing each element in the output sequence precludes their use in online settings and results in a quadratic time complexity. Based on the insight that the alignment between input and output sequence elements is monotonic in many problems of interest, we propose an end-to-end differentiable method for learning monotonic alignments which, at test time, enables computing attention online and in linear time. We validate our approach on sentence summarization, machine translation, and online speech recognition problems and achieve results competitive with existing sequence-to-sequence models.

PaperPDFConference PDFCode

In Syntology Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

Code

craffel/mad officialmentioned in papermentioned on GitHubtf 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

Machine TranslationSentenceSentence SummarizationSpeech RecognitionText SummarizationTranslationspeech-recognition

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Speech Recognition TIMIT Soft Monotonic Attention (ours, offline) Percentage error 20.1 #20 of 22 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