Papers › Convolutional Sequence to Sequence Learning

Convolutional Sequence to Sequence Learning

8 May 2017ICML 2017 8arXiv:1705.03122archive 2025-07-28

Jonas Gehring, Michael Auli, David Grangier, Denis Yarats, Yann N. Dauphin

The prevalent approach to sequence to sequence learning maps an input sequence to a variable length output sequence via recurrent neural networks. We introduce an architecture based entirely on convolutional neural networks. Compared to recurrent models, computations over all elements can be fully parallelized during training and optimization is easier since the number of non-linearities is fixed and independent of the input length. Our use of gated linear units eases gradient propagation and we equip each decoder layer with a separate attention module. We outperform the accuracy of the deep LSTM setup of Wu et al. (2016) on both WMT'14 English-German and WMT'14 English-French translation at an order of magnitude faster speed, both on GPU and CPU.

PaperPDFConference PDFCode

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

Code

37 repositories listed; official and paper-mentioned ones first.

facebookresearch/fairseq officialmentioned in papermentioned on GitHubpytorchMIT report
CKPOON0619/Kaggle2Sigma mentioned on GitHub report
Deeksha96/Im2Latex mentioned on GitHubtf report
EdinburghNLP/XSum mentioned on GitHubpytorchMIT report
Helsinki-NLP/OpenNMT-py mentioned on GitHubpytorchMIT report
IBM/pytorch-seq2seq mentioned on GitHubpytorch report
Izecson/saml-nmt mentioned on GitHubmxnet report
Izecson/sockeye-1.16.6 mentioned on GitHubtf report
Kakoedlinnoeslovo/fairseq mentioned on GitHubtf report
MiuGod0126/ConvS2S_Paddle mentioned on GitHubpaddleApache-2.0 report
Nick-Zhao-Engr/Machine-Translation mentioned on GitHubpytorch report
OpenNMT/OpenNMT-py mentioned on GitHubpytorch report
YizhuLiu/sumlen mentioned on GitHubpytorch report
ZurichNLP/sockeye mentioned on GitHubmxnetApache-2.0 report
albarji/neurowriter mentioned on GitHubtf report
awslabs/sockeye mentioned on GitHubmxnetApache-2.0 report
bcmi220/esc4nmt mentioned on GitHubpytorch report
butsugiri/shape mentioned on GitHubpytorch report
cove-adml/adml-anon mentioned on GitHubpytorch report
facebookresearch/ParlAI mentioned on GitHubpytorchMIT report
lucylow/En_francais_si_vous_plait- mentioned on GitHubpytorchMIT report
memray/OpenNMT-kpg-release mentioned on GitHubpytorchMIT report
midobal/OpenNMT-py mentioned on GitHubpytorchMIT report
nrc-cnrc/sockeye-multisource mentioned on GitHubmxnet report
oneTimePad/conv-nmt mentioned on GitHubtf report
phanideepgampa/IM2LATEX mentioned on GitHubtf report
richinkabra/CoVe-BCN mentioned on GitHubpytorch report
shashiongithub/XSum mentioned on GitHubpytorchMIT report
siyuofzhou/CNNSeqToSeq mentioned on GitHubtorch report
thinkwee/DPP_CNN_Summarization mentioned on GitHubpytorch report
umeiko/mindspore-seq2seq mentioned on GitHubmindspore report
xingniu/sockeye mentioned on GitHubmxnet report
yinghao1019/NLP_and_DL_practice 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

Bangla Spelling Error CorrectionDecoderImage ClassificationMachine TranslationTranslation

2 archive task tags without a task page not shown.

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Bangla Spelling Error Correction DPCSpell-Bangla-SEC-Corpus ConvSeq2Seq Exact Match Accuracy 78.85% #3 of 4 Archive leaderboard report
Image Classification MNIST CNN Model by Som Accuracy 98.59 #51 of 81 Archive leaderboard report
Image Classification MNIST CNN Model by Som Percentage error 1.41 #51 of 81 Archive leaderboard report
Machine Translation IWSLT2015 English-German ConvS2S BLEU score 26.73 #6 of 8 Archive leaderboard report
Machine Translation IWSLT2015 German-English ConvS2S BLEU score 32.31 #6 of 15 Archive leaderboard report
Machine Translation WMT2014 English-French ConvS2S (ensemble) BLEU score 41.3 #25 of 57 Archive leaderboard report
Machine Translation WMT2014 English-French ConvS2S BLEU score 40.46 #33 of 57 Archive leaderboard report
Machine Translation WMT2014 English-French ConvS2S Hardware Burden 143G #33 of 57 Archive leaderboard report
Machine Translation WMT2014 English-German ConvS2S (ensemble) BLEU score 26.4 #58 of 91 Archive leaderboard report
Machine Translation WMT2014 English-German ConvS2S (ensemble) Hardware Burden 54G #58 of 91 Archive leaderboard report
Machine Translation WMT2014 English-German ConvS2S BLEU score 25.16 #70 of 91 Archive leaderboard report
Machine Translation WMT2014 English-German ConvS2S Hardware Burden 72G #70 of 91 Archive leaderboard report
Machine Translation WMT2016 English-Romanian ConvS2S BPE40k BLEU score 29.9 #7 of 21 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

LSTMSigmoid ActivationTanh Activation

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