Papers › Joint Source-Target Self Attention with Locality Constraints

Joint Source-Target Self Attention with Locality Constraints

16 May 2019arXiv:1905.06596archive 2025-07-28

José A. R. Fonollosa, Noe Casas, Marta R. Costa-jussà

The dominant neural machine translation models are based on the encoder-decoder structure, and many of them rely on an unconstrained receptive field over source and target sequences. In this paper we study a new architecture that breaks with both conventions. Our simplified architecture consists in the decoder part of a transformer model, based on self-attention, but with locality constraints applied on the attention receptive field. As input for training, both source and target sentences are fed to the network, which is trained as a language model. At inference time, the target tokens are predicted autoregressively starting with the source sequence as previous tokens. The proposed model achieves a new state of the art of 35.7 BLEU on IWSLT'14 German-English and matches the best reported results in the literature on the WMT'14 English-German and WMT'14 English-French translation benchmarks.

PaperPDFCode

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

Code

jarfo/joint officialmentioned in papermentioned on GitHubpytorch report
lkfo415579/joint mentioned on GitHubpytorch 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

DecoderLanguage ModelingLanguage ModellingMachine TranslationTranslation

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Machine Translation IWSLT2014 German-English Local Joint Self-attention BLEU score 35.7 #20 of 34 Archive leaderboard report
Machine Translation WMT2014 English-French Local Joint Self-attention BLEU score 43.3 #10 of 57 Archive leaderboard report
Machine Translation WMT2014 English-German Local Joint Self-attention BLEU score 29.7 #19 of 91 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.

Methods

Absolute Position EncodingsAdamAttentionBPEDense ConnectionsDropoutLabel SmoothingLayer NormalizationLinear LayerMulti-Head AttentionPosition-Wise Feed-Forward LayerReLUResidual ConnectionSoftmaxTransformer

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