Papers › Sparse Sequence-to-Sequence Models

Sparse Sequence-to-Sequence Models

14 May 2019ACL 2019 7arXiv:1905.05702archive 2025-07-28

Ben Peters, Vlad Niculae, André F. T. Martins

Sequence-to-sequence models are a powerful workhorse of NLP. Most variants employ a softmax transformation in both their attention mechanism and output layer, leading to dense alignments and strictly positive output probabilities. This density is wasteful, making models less interpretable and assigning probability mass to many implausible outputs. In this paper, we propose sparse sequence-to-sequence models, rooted in a new family of α-entmax transformations, which includes softmax and sparsemax as particular cases, and is sparse for any α> 1. We provide fast algorithms to evaluate these transformations and their gradients, which scale well for large vocabulary sizes. Our models are able to produce sparse alignments and to assign nonzero probability to a short list of plausible outputs, sometimes rendering beam search exact. Experiments on morphological inflection and machine translation reveal consistent gains over dense 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

deep-spin/entmax officialmentioned in paperpytorch 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 TranslationMorphological InflectionTranslation

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

Methods

SoftmaxSparsemax

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