Papers › Neural Machine Translation by Jointly Learning to Align and Translate

Neural Machine Translation by Jointly Learning to Align and Translate

1 Sep 2014arXiv:1409.0473archive 2025-07-28

Dzmitry Bahdanau, Kyunghyun Cho, Yoshua Bengio

Neural machine translation is a recently proposed approach to machine translation. Unlike the traditional statistical machine translation, the neural machine translation aims at building a single neural network that can be jointly tuned to maximize the translation performance. The models proposed recently for neural machine translation often belong to a family of encoder-decoders and consists of an encoder that encodes a source sentence into a fixed-length vector from which a decoder generates a translation. In this paper, we conjecture that the use of a fixed-length vector is a bottleneck in improving the performance of this basic encoder-decoder architecture, and propose to extend this by allowing a model to automatically (soft-)search for parts of a source sentence that are relevant to predicting a target word, without having to form these parts as a hard segment explicitly. With this new approach, we achieve a translation performance comparable to the existing state-of-the-art phrase-based system on the task of English-to-French translation. Furthermore, qualitative analysis reveals that the (soft-)alignments found by the model agree well with our intuition.

PaperPDFCodeCode Syntology ran

In Syntology View this paper on Syntology, its page in Syntology's graph. That page adds which of its functions are also present in other papers' code Syntology holds, with dates, and its dated run record as JSON and a README badge. It also lists the repositories linked to the paper, the abstract and the calls for agents.

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

For agents, on Syntology's MCP service (how to connect):

Code

Syntology 44 code samples harvested from 14 repositories linked to this paper: 41 ran (of which 2 constructed an object rather than computing a result; 24 with no instrument failure: 4 honoured, 0 violated, 20 with no contract checked; 17 where Syntology's instrument failed) · 3 unverified. Where Syntology's instrument failed: 17 where our contract draft was wrong; failures of Syntology's instrument, not of the code.

By repository: community (archive-listed): 44 samples from 14 repositories, 41 ran (24 with no instrument failure; 17 where Syntology's instrument failed). The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

No sample is linked to this paper from 22 of its repositories that Syntology harvested for other papers:

Levels written between 2026-09-22 and 2026-09-26 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed. 1 of the 41 samples that ran has no recorded date.

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

A-Jacobson/minimal-nmt mentioned on GitHubpytorchMITSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Massive Exploration of Neural Machine Translation Architectures (arXiv:1703.03906; that paper's own run record: 6 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 0 violated, 5 with no contract checked; 1 where Syntology's instrument failed) · 3 unverified); nothing checks that they implement this paper's method. report
AMNAALMGLY/NLP mentioned on GitHubSyntology: not harvested report
AaronCCWong/Show-Attend-and-Tell mentioned on GitHubpytorchSyntology: not harvested report
Baichenjia/NMT-eager mentioned on GitHubtfSyntology: 4 samples, 4 ran (4 instrument-failed) · 0 unverified report
Cenrax/Image-Captioning-with-Translation- mentioned on GitHubtfSyntology: not harvested report
DCYN/Ramdomized-Clinical-Trail-Classification mentioned on GitHubtfSyntology: not harvested report
Epoch-Mengying/Generating-Poetry-with-Chatbot mentioned on GitHubSyntology: not harvested report
EuphoriaYan/ChatRobot-For-Keras2 mentioned on GitHubtfSyntology: not harvested report
Glaceon31/Document-Transformer mentioned on GitHubtfBSD-3-ClauseSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Improving the Transformer Translation Model with Document-Level Context (arXiv:1810.03581; that paper's own run record: 1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 11 unverified); nothing checks that they implement this paper's method. report
Guillem96/pointer-nn-pytorch mentioned on GitHubpytorchSyntology: 2 samples, 2 ran (0 instrument-failed) · 0 unverified report
HemaDevaSagar35/NeuralMachineTranslation-French2English mentioned on GitHubtfSyntology: not harvested report
IS5882/Open-CyKG mentioned on GitHubtfSyntology: not harvested report
IpastorSan/seq2seq-with-attention-OCR-translation mentioned on GitHubtfApache-2.0Syntology: 4 samples, 4 ran (0 instrument-failed) · 0 unverified report
Izecson/saml-nmt mentioned on GitHubmxnetSyntology: not harvested report
Izecson/sockeye-1.16.6 mentioned on GitHubtfSyntology: not harvested report
JRC1995/Abstractive-Summarization mentioned on GitHubtfSyntology: not harvested report
Matthewdowney18/Yelp_attention mentioned on GitHubpytorchSyntology: not harvested report
Matthewdowney18/Yelp_seq2seq mentioned on GitHubpytorchSyntology: not harvested report
Nick-Zhao-Engr/Machine-Translation mentioned on GitHubpytorchSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Learning Phrase Representations using RNN Encoder-Decoder for Statistical Machine Translation (arXiv:1406.1078; that paper's own run record: 13 ran (of which 6 constructed an object rather than computing a result; 10 with no instrument failure: 0 honoured, 0 violated, 10 with no contract checked; 3 where Syntology's instrument failed) · 9 unverified); nothing checks that they implement this paper's method. report
ScientiaEtVeritas/NeuralMachineTranslation mentioned on GitHubpytorchSyntology: not harvested report
Shubham-SK/TreeOverAte mentioned on GitHubpytorchSyntology: not harvested report
Shubham-SK/kronos mentioned on GitHubpytorchSyntology: not harvested report
SimonDele/Glossary mentioned on GitHubSyntology: not harvested report
SwordYork/DCNMT mentioned on GitHubGPL-3.0Syntology: not harvested report
THUNLP-MT/THUMT mentioned on GitHubtfSyntology: 1 sample, 1 ran (1 instrument-failed) · 0 unverified report
TellinaTool/nl2bash mentioned on GitHubtfGPL-3.0Syntology: not harvested report
YvesWang/Machine_Translation_NLP mentioned on GitHubpytorchSyntology: 3 samples, 3 ran (3 instrument-failed) · 0 unverified report
ZurichNLP/sockeye mentioned on GitHubmxnetApache-2.0Syntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Domain Robustness in Neural Machine Translation (arXiv:1911.03109; that paper's own run record: 10 ran (of which 0 constructed an object rather than computing a result; 10 with no instrument failure: 0 honoured, 0 violated, 10 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified); nothing checks that they implement this paper's method. report
aaaceo890/Attention mentioned on GitHubpytorchSyntology: not harvested report
abhishekr7/Summarization-of-Radiological-Reports mentioned on GitHubGPL-3.0Syntology: not harvested report
abmitra84/Machine_Translation mentioned on GitHubSyntology: not harvested report
astorfi/neural-machine-translation-from-scratch mentioned on GitHubpytorchSyntology: not harvested report
astorfi/sequence-to-sequence-from-scratch mentioned on GitHubpytorchSyntology: not harvested report
atpaino/deep-text-corrector mentioned on GitHubtfApache-2.0Syntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Grammar as a Foreign Language (arXiv:1412.7449; that paper's own run record: 9 ran (of which 0 constructed an object rather than computing a result; 9 with no instrument failure: 0 honoured, 0 violated, 9 with no contract checked; 0 where Syntology's instrument failed) · 8 unverified); nothing checks that they implement this paper's method. report
awslabs/sockeye mentioned on GitHubmxnetApache-2.0Syntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to CoCoA-MT: A Dataset and Benchmark for Contrastive Controlled MT with Application to Formality (arXiv:2205.04022; that paper's own run record: 10 ran (of which 0 constructed an object rather than computing a result; 10 with no instrument failure: 0 honoured, 0 violated, 10 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified); nothing checks that they implement this paper's method. report
b-etienne/Seq2seq-PyTorch mentioned on GitHubpytorchSyntology: not harvested report
bentrevett/pytorch-seq2seq mentioned on GitHubpytorchMITSyntology: not harvested report
bkoch4142/attention-is-all-you-need-paper mentioned on GitHubpytorchSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Attention Is All You Need (arXiv:1706.03762; that paper's own run record: 610 ran (of which 293 constructed an object rather than computing a result; 529 with no instrument failure: 45 honoured, 15 violated, 469 with no contract checked; 81 where Syntology's instrument failed) · 336 unverified); nothing checks that they implement this paper's method. report
brainsqueeze/text2vec mentioned on GitHubtfSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Attention Is All You Need (arXiv:1706.03762; that paper's own run record: 610 ran (of which 293 constructed an object rather than computing a result; 529 with no instrument failure: 45 honoured, 15 violated, 469 with no contract checked; 81 where Syntology's instrument failed) · 336 unverified); nothing checks that they implement this paper's method. report
brightmart/text_classification mentioned on GitHubtfSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding (arXiv:1810.04805; that paper's own run record: 300 ran (of which 75 constructed an object rather than computing a result; 234 with no instrument failure: 18 honoured, 5 violated, 211 with no contract checked; 66 where Syntology's instrument failed) · 359 unverified); nothing checks that they implement this paper's method. report
chao-ji/tf-seq2seq mentioned on GitHubtfSyntology: not harvested report
chunghyunhee/twitter_disaster_NLP mentioned on GitHubSyntology: not harvested report
cosmoquester/seq2seq mentioned on GitHubtfSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Attention Is All You Need (arXiv:1706.03762; that paper's own run record: 610 ran (of which 293 constructed an object rather than computing a result; 529 with no instrument failure: 45 honoured, 15 violated, 469 with no contract checked; 81 where Syntology's instrument failed) · 336 unverified); nothing checks that they implement this paper's method. report
dalmia/Quora-Question-Pairs mentioned on GitHubtfGPL-3.0Syntology: not harvested report
daphne12345/SummarizationRadiologyReports mentioned on GitHubtfSyntology: not harvested report
datalogue/keras-attention mentioned on GitHubAGPL-3.0Syntology: not harvested report
deepsense-ai/unblackboxing_webinar mentioned on GitHubtfSyntology: not harvested report
distractor-generation/dg_survey mentioned on GitHubSyntology: not harvested report
dongdong199408/teachchatrobot mentioned on GitHubtfSyntology: not harvested report
eske/seq2seq mentioned on GitHubtfApache-2.0Syntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Listen and Translate: A Proof of Concept for End-to-End Speech-to-Text Translation (arXiv:1612.01744; that paper's own run record: 10 ran (of which 0 constructed an object rather than computing a result; 10 with no instrument failure: 0 honoured, 0 violated, 10 with no contract checked; 0 where Syntology's instrument failed) · 5 unverified); nothing checks that they implement this paper's method. report
farizrahman4u/seq2seq mentioned on GitHubSyntology: not harvested report
frozentoad9/Neural-Machine-Translation mentioned on GitHubpytorchSyntology: not harvested report
gongrennengzhi/nmt mentioned on GitHubSyntology: not harvested report
gongshuangshuang/deep-text-corrector mentioned on GitHubtfSyntology: not harvested report
graykode/nlp-tutorial mentioned on GitHubpytorchSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Efficient Estimation of Word Representations in Vector Space (arXiv:1301.3781; that paper's own run record: 43 ran (of which 7 constructed an object rather than computing a result; 38 with no instrument failure: 4 honoured, 0 violated, 34 with no contract checked; 5 where Syntology's instrument failed) · 19 unverified), Learning Phrase Representations using RNN Encoder-Decoder for Statistical Machine Translation (arXiv:1406.1078; that paper's own run record: 13 ran (of which 6 constructed an object rather than computing a result; 10 with no instrument failure: 0 honoured, 0 violated, 10 with no contract checked; 3 where Syntology's instrument failed) · 9 unverified), Attention Is All You Need (arXiv:1706.03762; that paper's own run record: 610 ran (of which 293 constructed an object rather than computing a result; 529 with no instrument failure: 45 honoured, 15 violated, 469 with no contract checked; 81 where Syntology's instrument failed) · 336 unverified) and 1 more (every one in this page's JSON twin); nothing checks that they implement this paper's method. report
harshithbelagur/Neural-Machine-Translation mentioned on GitHubtfSyntology: not harvested report
hiun/learning-transformers mentioned on GitHubpytorchSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Attention Is All You Need (arXiv:1706.03762; that paper's own run record: 610 ran (of which 293 constructed an object rather than computing a result; 529 with no instrument failure: 45 honoured, 15 violated, 469 with no contract checked; 81 where Syntology's instrument failed) · 336 unverified); nothing checks that they implement this paper's method. report
hnt4499/seq2seq mentioned on GitHubpytorchSyntology: 2 samples, 2 ran (1 instrument-failed) · 0 unverified report
huulinhcvp/chatBot mentioned on GitHubpytorchSyntology: not harvested report
insigh/THUMT mentioned on GitHubtfSyntology: not harvested report
jiangnanhugo/seq2seq_cuda mentioned on GitHubtfSyntology: not harvested report
jmyrberg/finnlem mentioned on GitHubtfSyntology: not harvested report
la-serene/English-German-Translation-System mentioned on GitHubtfApache-2.0Syntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Sequence to Sequence Learning with Neural Networks (arXiv:1409.3215; that paper's own run record: 21 ran (of which 0 constructed an object rather than computing a result; 13 with no instrument failure: 3 honoured, 0 violated, 10 with no contract checked; 8 where Syntology's instrument failed) · 4 unverified); nothing checks that they implement this paper's method. report
labdac/charlacompling mentioned on GitHubSyntology: not harvested report
laserene/English-German-Translation-System mentioned on GitHubtfApache-2.0Syntology: not harvested report
ldulcic/chatbot mentioned on GitHubpytorchSyntology: not harvested report
leob03/Image_captionning mentioned on GitHubpytorchMITSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Show, Attend and Tell: Neural Image Caption Generation with Visual Attention (arXiv:1502.03044; that paper's own run record: 58 ran (of which 0 constructed an object rather than computing a result; 45 with no instrument failure: 3 honoured, 0 violated, 42 with no contract checked; 13 where Syntology's instrument failed) · 26 unverified); nothing checks that they implement this paper's method. report
lkfo415579/MT-Readling-List mentioned on GitHubtfSyntology: not harvested report
lucylow/En_francais_si_vous_plait- mentioned on GitHubpytorchMITSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to fairseq: A Fast, Extensible Toolkit for Sequence Modeling (arXiv:1904.01038; that paper's own run record: 3 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 1 where Syntology's instrument failed) · 8 unverified); nothing checks that they implement this paper's method. report
mayurnewase/Translation mentioned on GitHubSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Attention Is All You Need (arXiv:1706.03762; that paper's own run record: 610 ran (of which 293 constructed an object rather than computing a result; 529 with no instrument failure: 45 honoured, 15 violated, 469 with no contract checked; 81 where Syntology's instrument failed) · 336 unverified); nothing checks that they implement this paper's method. report
mike-a-yen/date-translation mentioned on GitHubpytorchSyntology: not harvested report
mindspore-courses/DeepNLP-models-MindSpore mentioned on GitHubmindsporeApache-2.0Syntology: not harvested report
moon23k/Attention_Anchors mentioned on GitHubpytorchSyntology: not harvested report
mp2893/gram mentioned on GitHubBSD-3-ClauseSyntology: not harvested report
mpavlovic/insincere-questions-classifier mentioned on GitHubtfMITSyntology: 5 samples, 4 ran (0 instrument-failed) · 1 unverified report
neqkir/attention-mechanism mentioned on GitHubtfSyntology: not harvested report
nrc-cnrc/sockeye-multisource mentioned on GitHubmxnetSyntology: not harvested report
nvshrao/AlignAndTranslate mentioned on GitHubSyntology: not harvested report
philipperemy/keras-attention-mechanism mentioned on GitHubtfApache-2.0Syntology: not harvested report
prakhargurawa/Neural-Machine-Translation-Keras-Attention mentioned on GitHubtfSyntology: 2 samples, 2 ran (1 instrument-failed) · 0 unverified report
prakhargurawa/Neural-Machine-Translation-Keras-German-English mentioned on GitHubtfMITSyntology: 3 samples, 3 ran (0 instrument-failed) · 0 unverified report
qq345736500/sarcasm mentioned on GitHubtfMITSyntology: 8 samples, 6 ran (0 instrument-failed) · 2 unverified report
rileynwong/pytorch-seq2seq-joke2punchline mentioned on GitHubpytorchSyntology: 4 samples, 4 ran (4 instrument-failed) · 0 unverified report
sambit9238/deep_text_corrector mentioned on GitHubtfApache-2.0Syntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Grammar as a Foreign Language (arXiv:1412.7449; that paper's own run record: 9 ran (of which 0 constructed an object rather than computing a result; 9 with no instrument failure: 0 honoured, 0 violated, 9 with no contract checked; 0 where Syntology's instrument failed) · 8 unverified); nothing checks that they implement this paper's method. report
schwartznir/AbstrEncap mentioned on GitHubtfSyntology: not harvested report
sen-pai/audio-word2vec-pytorch mentioned on GitHubpytorchSyntology: not harvested report
sh951011/Attention-Implementation mentioned on GitHubpytorchMITSyntology: not harvested report
shawnyxiao/textclassification-keras mentioned on GitHubtfMITSyntology: not harvested report
shlokmehrotra/Convocare mentioned on GitHubpytorchSyntology: not harvested report
simonjisu/NMT mentioned on GitHubpytorchMITSyntology: 1 sample, 1 ran (1 instrument-failed) · 0 unverified report
slme1109/Lyrics_Generator_Using_LSTM mentioned on GitHubtfSyntology: not harvested report
slme1109/lyrics-generator mentioned on GitHubtfSyntology: not harvested report
smisthzhu/attentionocr mentioned on GitHubtfSyntology: not harvested report
sooftware/Attention-Implementation mentioned on GitHubpytorchSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Attention Is All You Need (arXiv:1706.03762; that paper's own run record: 610 ran (of which 293 constructed an object rather than computing a result; 529 with no instrument failure: 45 honoured, 15 violated, 469 with no contract checked; 81 where Syntology's instrument failed) · 336 unverified) and Transformer-XL: Attentive Language Models Beyond a Fixed-Length Context (arXiv:1901.02860; that paper's own run record: 67 ran (of which 37 constructed an object rather than computing a result; 49 with no instrument failure: 4 honoured, 1 violated, 44 with no contract checked; 18 where Syntology's instrument failed) · 76 unverified); nothing checks that they implement this paper's method. report
sooftware/attentions mentioned on GitHubpytorchMITSyntology: not harvested report
sooftware/nlp-attentions mentioned on GitHubpytorchMITSyntology: not harvested report
sunnysinghnitb/text-corrector-software mentioned on GitHubtfApache-2.0Syntology: not harvested report
sunnysinghnitb/text_corrector_software mentioned on GitHubtfApache-2.0Syntology: not harvested report
suryachintu/Quora-Insincere-Questions-Kaggle mentioned on GitHubSyntology: not harvested report
thomlake/pytorch-attention mentioned on GitHubpytorchBSD-2-ClauseSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Pointer Networks (arXiv:1506.03134; that paper's own run record: 18 ran (of which 0 constructed an object rather than computing a result; 13 with no instrument failure: 3 honoured, 1 violated, 9 with no contract checked; 5 where Syntology's instrument failed) · 5 unverified); nothing checks that they implement this paper's method. report
thumt/THUMT mentioned on GitHubtfSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Self-Attention with Relative Position Representations (arXiv:1803.02155; that paper's own run record: 13 ran (of which 4 constructed an object rather than computing a result; 8 with no instrument failure: 2 honoured, 0 violated, 6 with no contract checked; 5 where Syntology's instrument failed) · 10 unverified); nothing checks that they implement this paper's method. report
thunlp-mt/ckd mentioned on GitHubpytorchSyntology: 2 samples, 2 ran (2 instrument-failed) · 0 unverified report
thunlp/TensorFlow-Summarization mentioned on GitHubtfMITSyntology: 3 samples, 3 ran (0 instrument-failed) · 0 unverified report
tree-park/kor-to-eng-translation mentioned on GitHubpytorchSyntology: not harvested report
umeiko/mindspore-seq2seq mentioned on GitHubmindsporeSyntology: not harvested report
umutguneri/Question-Answering-Assistant mentioned on GitHubtfSyntology: not harvested report
vGkatsis/Chat_Bot_DL mentioned on GitHubpytorchSyntology: not harvested report
varun-bhaseen/Image-caption-generation-using-attention-model mentioned on GitHubtfSyntology: not harvested report
vikua/keras-attention-models mentioned on GitHubSyntology: not harvested report
wangmz15/Chinese-Error-Correction-with-THUMT mentioned on GitHubtfSyntology: not harvested report
xhlulu/arxiv-assistant mentioned on GitHubSyntology: not harvested report
xingniu/sockeye mentioned on GitHubmxnetSyntology: not harvested report
yinghao1019/NLP_and_DL_practice mentioned on GitHubpytorchSyntology: not harvested report
ykrmm/ICLR_2020 mentioned on GitHubpytorchSyntology: not harvested report
ykrmm/TREMBA mentioned on GitHubpytorchSyntology: not harvested report
yurayli/stanford-cs224n-sol mentioned on GitHubpytorchSyntology: not harvested report
zhang0jhon/AttentionOCR mentioned on GitHubtfSyntology: not harvested report
2023-MindSpore-1/ms-code-200 mindsporeSyntology: not harvested report
MindSpore-paper-code-3/code9 mindsporeSyntology: not harvested report
uzi0espil/research-papers-implementation tfSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Attention Is All You Need (arXiv:1706.03762; that paper's own run record: 610 ran (of which 293 constructed an object rather than computing a result; 529 with no instrument failure: 45 honoured, 15 violated, 469 with no contract checked; 81 where Syntology's instrument failed) · 336 unverified) and An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale (arXiv:2010.11929; that paper's own run record: 307 ran (of which 165 constructed an object rather than computing a result; 286 with no instrument failure: 8 honoured, 2 violated, 276 with no contract checked; 21 where Syntology's instrument failed) · 112 unverified); nothing checks that they implement this paper's method. 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.

A paper named beside a repository with no sample linked to this paper is shown with that paper's own run record, not this paper's: “ran” means executed on a synthesized input, not that the code is correct, and “where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. Papers are listed in arXiv-id order, at most three per repository.

Code Syntology ran Syntology

44 samples harvested: 41 ran (of which 2 constructed an object rather than computing a result; 24 with no instrument failure: 4 honoured, 0 violated, 20 with no contract checked; 17 where Syntology's instrument failed) · 3 unverified. “Where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. Syntology's record for this page has not changed since , the first build that kept a record date for it; when this build read Syntology's graph is in the build record. That date is not when the samples ran.

4ran · honoured contract
17ran · our draft was wrong
20ran
3unverified

Licence: 16 of the 44 samples are pointer only, meaning Syntology does not serve that copy's text. This page shows no code text for any sample; each one links to its file in the repository.

Harvested from 14 repositories linked to this paper, official or community; the list below is grouped by repository, each group headed by its name and what it is to the paper. 8 samples whose link to this paper records no repository are listed under one of this paper's own repositories, because identical code was harvested from it for another paper. “Ran” means the sample executed on a synthesized input. It does not mean the output is correct, and nothing here reproduces the paper's results. A line beginning “fixture:” under a sample that ran gives the arguments Syntology's fixture called the sample with, each as name:type/rank/element kind (? where none was recorded), and the type of what the fixture's run returned, exactly as the harness recorded them; the arguments and the returned type were recorded by two separate runs of the same fixture. No output value is shown, and a returned type says nothing about whether the output was right. “Level recorded” gives the UTC date when Syntology's graph wrote the sample's verification level, not when the code executed; where the level was written before Syntology's graph kept that date, the row says “level recorded, date not recorded”. “Honoured” and “violated” refer to a contract Syntology drafted from the code itself. “Our draft was wrong” and “the contract check could not run” are failures of Syntology's instrument, not of the code: the sample ran on Syntology's synthesized input, and then the drafted contract did not describe it, or the check itself raised an error (RAISES), lacked a dependency (DEP_MISSING) or ran out of time (TIMEOUT); hover the label for which. A metamorphic tier, where shown, is evidence of the output's shape, not that the sample implements the method.

Each sample ends with its code_sha256. A sample's code_sha256 is Syntology's identity for that exact code. It is printed in full (16 hexadecimal characters for every sample in this build), and get_code(code_sha256="…") takes it exactly as printed. An agent calls it on Syntology's MCP service (how to connect); click an identity to copy that call.

Repository labels, per sample. official repository: The archive marks this repository official for the paper. named in the paper: The archive records that the paper mentions this repository; it is not marked official. community (archive-listed): In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper. found in paper text by Syntology: Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted. community: Not in the archive's code links for this paper; a community repository Syntology harvested. Samples are grouped by repository: a repository marked official first, then by how directly the repository is tied to the paper, then in the archive's order; never by how many ran. Licence labels name the repository's licence as recorded at harvest. “Pointer only” means Syntology does not serve that copy's text, for one of six reasons: no licence file was found; the licence was not identified; the licence is recorded as permissive but that copy's record is not marked cleared; the licence is outside the permissive list Syntology serves text under (MIT, Apache-2.0, BSD and similar); this paper's copy was not located, so its licence is not recorded; or this paper's copy is cleared, but the stored copy of the same code that Syntology serves is not. Some licences outside that list permit redistribution, such as WTFPL, and GPL-3.0 under its conditions; they are simply not on the list. Hover a licence label for the reason. File links open the file on GitHub at the default branch, which may have changed since the harvest.

A function or class name links to its page when the name occurs in the harvested code of at least 5 papers; the name is a string, not an identity. A census tag appears when Syntology's census ran implementations with that name on one shared input per bucket: it gives how many were compared, from how many papers, and how many distinct outputs they produced, and names this sample's bucket when this sample was one of them.

Baichenjia/NMT-eager community (archive-listed) 4 samples, 4 ran (4 instrument-failed) · 0 unverified
create_dataset in 47 papers NMT-eager.py ran · our draft was wrong no licence file found · pointer only · 6294101bad54572d · report fixture: signature path:str/0/str, num_examples:int/0/int · returned list · level recorded 2026-09-22
preprocess_chinese NMT-eager-chinese-eng.py ran · our draft was wrong fingerprinted no licence file found · pointer only · 72f8e5deeaf2f42f · report fixture: signature w:str/0/str · returned str · level recorded 2026-09-22
preprocess_eng NMT-eager-chinese-eng.py ran · our draft was wrong fingerprinted no licence file found · pointer only · d23765a7df2697f9 · report fixture: signature w:str/0/str · returned str · level recorded 2026-09-22
preprocess_sentence NMT-eager.py ran · our draft was wrong fingerprinted no licence file found · pointer only · cd26c09003aad137 · report fixture: signature w:str/0/str · returned str · level recorded 2026-09-22
Guillem96/pointer-nn-pytorch community (archive-listed) 2 samples, 2 ran (0 instrument-failed) · 0 unverified
batch in 31 papers data.py identical code Syntology harvested from this repository for another paper; this paper's link records no repository, path or licence of its own ran · honoured contract licence of this copy not recorded · 796b2511367209ba · report fixture: signature batch_size:int/0/int, min_len:int/0/int, max_len:int/0/int · returned tuple · level recorded 2026-09-22
sample in 167 papers
census: 8 implementations from 9 papers, 7 distinct outputs across 5 buckets, one shared input per bucket
data.py identical code Syntology harvested from this repository for another paper; this paper's link records no repository, path or licence of its own ran · honoured contract fingerprinted licence of this copy not recorded · 8b887331144b7967 · report fixture: signature min_length:int/0/int, max_length:int/0/int · returned tuple · level recorded 2026-09-22
IpastorSan/seq2seq-with-attention-OCR-translation community (archive-listed) 4 samples, 4 ran (0 instrument-failed) · 0 unverified
max_len model/attention_seq2seq/seq2seq_model_with_attention.py ran Apache-2.0 (permissive) · f5175a54203ad8ea · report fixture: signature data:list/1/str · returned int · level recorded 2026-09-26
open_data model/ocr_text_recognition.py ran Apache-2.0 (permissive) · 6d38556f066c4b14 · report fixture: signature dataset:str/0/str, num_examples:int/0/int · returned list · level recorded 2026-09-26
open_txt model/text_preprocessing.py ran Apache-2.0 (permissive) · cfd02a8466a5c1e8 · report fixture: signature dataset:str/0/str · returned str · level recorded 2026-09-26
unicode_to_ascii in 6 papers model/text_preprocessing.py ran fingerprinted Apache-2.0 (permissive) · 65942c6c527f361b · report fixture: signature text:str/0/str · returned str · level recorded 2026-09-26
THUNLP-MT/THUMT community (archive-listed) 1 sample, 1 ran (1 instrument-failed) · 0 unverified
parse_args in 355 papers thumt/bin/trainer.py ran · our draft was wrong BSD-3-Clause (permissive) · f83b8f1f177c138e · report fixture: signature args:list/1/str · returned Namespace · level recorded 2026-09-22
YvesWang/Machine_Translation_NLP community (archive-listed) 3 samples, 3 ran (3 instrument-failed) · 0 unverified
LayerNorm in 121 papers
census: 5 implementations from 5 papers, 5 distinct outputs across 3 buckets, one shared input per bucket
Transformer/Decoder_Transformer.py ran · our draft was wrong no licence file found · pointer only · 02408cb7d7b045d1 · report fixture: signature embedding_dim:int/0/int · returned LayerNorm · level recorded 2026-09-22
Linear in 127 papers Transformer/Decoder_Transformer.py ran · our draft was wrong no licence file found · pointer only · 10865bbb99140edd · report fixture: signature in_features:int/0/int, out_features:int/0/int, bias:bool/0/bool · returned Linear · level recorded 2026-09-22
sequence_mask in 55 papers
census: 12 implementations from 15 papers, 5 distinct outputs across 2 buckets, one shared input per bucket this sample: bucket 1 of 2, arg 1: rank 1, kind int, dtype int64
AttentionRNN/Multilayers_Decoder.py ran · our draft was wrong fingerprinted no licence file found · pointer only · 149c4508c7494e2a · report fixture: signature lengths:Tensor/1/int · returned Tensor · level recorded 2026-09-22
hnt4499/seq2seq community (archive-listed) 2 samples, 2 ran (1 instrument-failed) · 0 unverified
count_parameters in 278 papers seq2seq/model.py identical code Syntology harvested from this repository for another paper; this paper's link records no repository, path or licence of its own ran · honoured contract licence of this copy not recorded · 0f26a596e83c5565 · report fixture: signature model:callable/0/? · returned int · level recorded 2026-09-22
parse_arguments in 61 papers scripts/train_and_evaluate.py identical code Syntology harvested from this repository for another paper; this paper's link records no repository, path or licence of its own ran · our draft was wrong licence of this copy not recorded · 2a74b7a19b47b566 · report fixture: signature argv:list/1/str · returned Namespace · level recorded 2026-09-22
mpavlovic/insincere-questions-classifier community (archive-listed) 5 samples, 4 ran (0 instrument-failed) · 1 unverified
build_model in 469 papers build_model.py ran MIT (permissive) · 01cec36b70027919 · report fixture: signature hparams:dict/0/?, embedding_matrix:ndarray/2/float · returned Functional · level recorded 2026-09-26
clean_contractions utils.py ran MIT (permissive) · f3a2acb3ab6ac45d · report fixture: signature text:str/0/str, mapping:dict/0/? · returned str · level recorded 2026-09-26
correct_spelling submission_script.py ran MIT (permissive) · b7993440578a50e0 · report fixture: signature text:str/0/str, mapping:dict/0/? · returned str · level recorded 2026-09-26
load_train_data in 8 papers submission_script.py ran MIT (permissive) · 15021775e16a477e · report fixture: signature file_path:str/0/str, train_column:str/0/str, label_columns:list/1/str · returned tuple · level recorded 2026-09-26
clean_special_chars submission_script.py unverified MIT (permissive) · d8dfaa83f9283e10 · report
prakhargurawa/Neural-Machine-Translation-Keras-Attention community (archive-listed) 2 samples, 2 ran (1 instrument-failed) · 0 unverified
load_clean_sentences translation_neural_network_model.py ran · our draft was wrong MIT (permissive) · 5a7a5d4f405c2fd5 · report fixture: signature filename:str/0/str · returned list · level recorded 2026-09-22
max_length translation_neural_network_model.py ran · honoured contract MIT (permissive) · 64ded720acd0ec65 · report fixture: signature lines:list/1/str · returned int · level recorded 2026-09-22
prakhargurawa/Neural-Machine-Translation-Keras-German-English community (archive-listed) 3 samples, 3 ran (0 instrument-failed) · 0 unverified
create_tokenizer in 8 papers translation_neural_network_model.py ran MIT (permissive) · ad4e30338e48aa2c · report fixture: signature lines:list/1/str · returned Tokenizer · level recorded 2026-09-26
load_clean_sentences translation_evaluation_model.py ran MIT (permissive) · 250a25c8c9e1b730 · report fixture: signature filename:str/0/str · returned list · level recorded 2026-09-26
load_doc translation_preprocessing.py ran MIT (permissive) · 23e3b013d3d7c0e3 · report fixture: signature filename:str/0/str · returned str · level recorded 2026-09-26
qq345736500/sarcasm community (archive-listed) 8 samples, 6 ran (0 instrument-failed) · 2 unverified
build_model in 469 papers src/dl_models.py ran MIT (permissive) · 15bace44de8d1350 · report fixture: signature max_len:int/0/int, embedding_layer:callable/0/?, hidden_units:int/0/int, dropout:float/0/float, dnn_architecture:callable/0/? · returned Functional · level recorded 2026-09-26
build_subj_dicionary src/data_processing.py ran MIT (permissive) · f86db1bbd98544ec · report fixture: signature lines:list/1/str · returned dict · level recorded 2026-09-26
count_apparitions src/extract_baseline_features.py ran fingerprinted MIT (permissive) · 24b6069ed695e8f3 · report fixture: signature tokens:list/1/str, list_to_count_from:list/1/str · returned float · level recorded 2026-09-26
get_pos_features src/extract_statistical_features.py ran MIT (permissive) · 39685672f02e1067 · report fixture: signature pos_tweet:list/1/str · returned dict · level recorded 2026-09-26
get_regularization_params src/classifiers.py ran MIT (permissive) · 66e01a8e39117589 · report fixture: signature a:int/0/int, b:int/0/int, c:int/0/int, d:int/0/int, e:int/0/int · returned ndarray · level recorded 2026-09-26
select_active_features src/feature_analysis.py ran MIT (permissive) · ea2003016da44e7f · report fixture: signature all_features:list/1/dict, selected_features:list/1/str · returned list · level recorded 2026-09-26
get_sentiment_features src/extract_ml_features.py unverified MIT (permissive) · e5420ffff4171204 · report
perform_function src/feature_analysis.py unverified MIT (permissive) · 5a84cd52152103ed · report
rileynwong/pytorch-seq2seq-joke2punchline community (archive-listed) 4 samples, 4 ran (4 instrument-failed) · 0 unverified
normalize_string in 14 papers seq2seq.py identical code Syntology harvested from this repository for another paper; this paper's link records no repository, path or licence of its own ran · our draft was wrong fingerprinted licence of this copy not recorded · 0249f2927bd76913 · report fixture: signature s:str/0/str · returned str · level recorded 2026-09-22
readLangs seq2seq.py identical code Syntology harvested from this repository for another paper; this paper's link records no repository, path or licence of its own ran · our draft was wrong licence of this copy not recorded · 52625852fa241e82 · report fixture: signature lang1:str/0/str, lang2:str/0/str, reverse:bool/0/bool · returned tuple · level recorded 2026-09-22
readLangs joke2punchline.py ran · our draft was wrong no licence file found · pointer only · bd123a7513397989 · report fixture: signature lang1:str/0/str, lang2:str/0/str, reverse:bool/0/bool · returned tuple · level recorded 2026-09-22
unicode_to_ascii in 6 papers seq2seq.py identical code Syntology harvested from this repository for another paper; this paper's link records no repository, path or licence of its own ran · our draft was wrong fingerprinted licence of this copy not recorded · a2ec1e65cd2e8ef4 · report fixture: signature s:str/0/str · returned str · level recorded 2026-09-22
simonjisu/NMT community (archive-listed) 1 sample, 1 ran (1 instrument-failed) · 0 unverified
unicode_to_ascii in 6 papers model/preprocessing.py identical code Syntology harvested from this repository for another paper; this paper's link records no repository, path or licence of its own ran · our draft was wrong fingerprinted licence of this copy not recorded · 3b0218c9534b6ee7 · report fixture: signature s:str/0/str · returned str · level recorded, date not recorded
thunlp-mt/ckd community (archive-listed) 2 samples, 2 ran (2 instrument-failed) · 0 unverified
import_params in 9 papers thumt/bin/trainer.py ran · our draft was wrong BSD-3-Clause (permissive) · bb55d10bc8ee2bfa · report fixture: signature model_dir:str/0/str, model_name:str/0/str, params:MockParams/0/? · returned MockParams · level recorded 2026-09-22
parse_args in 355 papers thumt/bin/trainer.py ran · our draft was wrong BSD-3-Clause (permissive) · a172d56eb6c789db · report fixture: signature args:list/1/str · returned Namespace · level recorded 2026-09-22
thunlp/TensorFlow-Summarization community (archive-listed) 3 samples, 3 ran (0 instrument-failed) · 0 unverified
corpus_map2id src/data_util.py ran MIT (permissive) · 7d8cac963599093c · report fixture: signature data:list/1/list, tok2id:dict/0/? · returned tuple · level recorded 2026-09-26
create_dict src/data_util.py ran MIT (permissive) · e0be7626138d362f · report fixture: signature dict_path:str/0/str, corpus:list/1/list, max_vocab:int/0/int · returned tuple · level recorded 2026-09-26
load_dict in 29 papers src/data_util.py ran MIT (permissive) · 6354c695b0345eaa · report fixture: signature dict_path:str/0/str, max_vocab:NoneType/0/? · returned tuple · level recorded 2026-09-26

Tasks

Bangla Spelling Error CorrectionDecoderDialogue GenerationMachine TranslationSentenceTranslation

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Bangla Spelling Error Correction DPCSpell-Bangla-SEC-Corpus GRUSeq2Seq Exact Match Accuracy 75.56 #4 of 4 Archive leaderboard report
Dialogue Generation Persona-Chat Seq2Seq + Attention Avg F1 16.18 #4 of 6 Archive leaderboard report
Machine Translation IWSLT2015 German-English Bi-GRU (MLE+SLE) BLEU score 28.53 #11 of 15 Archive leaderboard report
Machine Translation WMT2014 English-French RNN-search50* BLEU score 36.2 #44 of 57 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

Tanh 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