Papers › Google's Neural Machine Translation System: Bridging the Gap between Human and Machine...

Google's Neural Machine Translation System: Bridging the Gap between Human and Machine Translation

26 Sep 2016arXiv:1609.08144archive 2025-07-28

Yonghui Wu, Mike Schuster, Zhifeng Chen, Quoc V. Le, Mohammad Norouzi, Wolfgang Macherey, Maxim Krikun, Yuan Cao, Qin Gao, Klaus Macherey, Jeff Klingner, Apurva Shah, Melvin Johnson, Xiaobing Liu, Łukasz Kaiser, Stephan Gouws, Yoshikiyo Kato, Taku Kudo, Hideto Kazawa, Keith Stevens, George Kurian, Nishant Patil, Wei Wang, Cliff Young, Jason Smith, Jason Riesa, Alex Rudnick, Oriol Vinyals, Greg Corrado, Macduff Hughes, Jeffrey Dean

Neural Machine Translation (NMT) is an end-to-end learning approach for automated translation, with the potential to overcome many of the weaknesses of conventional phrase-based translation systems. Unfortunately, NMT systems are known to be computationally expensive both in training and in translation inference. Also, most NMT systems have difficulty with rare words. These issues have hindered NMT's use in practical deployments and services, where both accuracy and speed are essential. In this work, we present GNMT, Google's Neural Machine Translation system, which attempts to address many of these issues. Our model consists of a deep LSTM network with 8 encoder and 8 decoder layers using attention and residual connections. To improve parallelism and therefore decrease training time, our attention mechanism connects the bottom layer of the decoder to the top layer of the encoder. To accelerate the final translation speed, we employ low-precision arithmetic during inference computations. To improve handling of rare words, we divide words into a limited set of common sub-word units ("wordpieces") for both input and output. This method provides a good balance between the flexibility of "character"-delimited models and the efficiency of "word"-delimited models, naturally handles translation of rare words, and ultimately improves the overall accuracy of the system. Our beam search technique employs a length-normalization procedure and uses a coverage penalty, which encourages generation of an output sentence that is most likely to cover all the words in the source sentence. On the WMT'14 English-to-French and English-to-German benchmarks, GNMT achieves competitive results to state-of-the-art. Using a human side-by-side evaluation on a set of isolated simple sentences, it reduces translation errors by an average of 60% compared to Google's phrase-based production system.

PaperPDFCodeCode Syntology ranMethod as code

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 46 code samples harvested from 7 repositories linked to this paper: 34 ran (of which 4 constructed an object rather than computing a result; 25 with no instrument failure: 1 honoured, 2 violated, 22 with no contract checked; 9 where Syntology's instrument failed) · 12 unverified. Where Syntology's instrument failed: 9 where our contract draft was wrong; failures of Syntology's instrument, not of the code.

By repository: community (archive-listed): 46 samples from 7 repositories, 34 ran (25 with no instrument failure; 9 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 6 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.

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

Automattic/wp-translate mentioned on GitHubtfSyntology: not harvested report
ChaiBapchya/mxnet-hardmax_machine_translation mentioned on GitHubmxnetSyntology: not harvested report
Liut2016/stackedResBiLSTM mentioned on GitHubtfSyntology: 5 samples, 1 ran (1 instrument-failed) · 4 unverified report
Nirvanabc/seq2seq-rnn mentioned on GitHubtfSyntology: not harvested report
SunbowLiu/CopyingPenalty mentioned on GitHubpytorchSyntology: not harvested report
ThAIKeras/bert mentioned on GitHubtfSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Neural Machine Translation of Rare Words with Subword Units (arXiv:1508.07909; that paper's own run record: 21 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; 20 where Syntology's instrument failed) · 9 unverified); nothing checks that they implement this paper's method. report
VladimirV99/Automatic-Translation mentioned on GitHubtfSyntology: not harvested report
ZHANG45/multi_gpu_seq2seq mentioned on GitHubpytorchSyntology: 6 samples, 5 ran (0 instrument-failed) · 1 unverified report
davidsvaughn/dts-tf mentioned on GitHubtfSyntology: not harvested report
facebookresearch/vizseq mentioned on GitHubSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to BERTScore: Evaluating Text Generation with BERT (arXiv:1904.09675; that paper's own run record: 44 ran (of which 4 constructed an object rather than computing a result; 10 with no instrument failure: 3 honoured, 2 violated, 5 with no contract checked; 34 where Syntology's instrument failed) · 32 unverified); nothing checks that they implement this paper's method. report
google/sentencepiece mentioned on GitHubtfApache-2.0Syntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Optimized Tokenization for Transcribed Error Correction (arXiv:2310.10704; that paper's own run record: 3 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified); nothing checks that they implement this paper's method. report
guillaume-chevalier/HAR-stacked-residual-bidir-LSTMs mentioned on GitHubtfApache-2.0Syntology: 2 samples, 1 ran (0 instrument-failed) · 1 unverified report
guillaume-chevalier/LSTM-Human-Activity-Recognition mentioned on GitHubtfMITSyntology: not harvested report
kh-kim/simple-nmt mentioned on GitHubpytorchSyntology: 5 samples, 3 ran (0 instrument-failed) · 2 unverified report
macco3k/deepstories mentioned on GitHubSyntology: not harvested report
microsoft/BlingFire mentioned on GitHubtfMITSyntology: 13 samples, 11 ran (2 instrument-failed) · 2 unverified report
nkjsy/Neural-Machine-Translation mentioned on GitHubtfSyntology: not harvested report
psunlpgroup/xsemplr mentioned on GitHubpytorchSyntology: 14 samples, 12 ran (5 instrument-failed) · 2 unverified report
sfu-natlang/SFUTranslate mentioned on GitHubpytorchGPL-3.0Syntology: not harvested report
sraj-whatdoesthedatasay/Capstone mentioned on GitHubtfSyntology: not harvested report
vchopin/GNMT_v2 mentioned on GitHubmindsporeApache-2.0Syntology: not harvested report
virsagothethird/Korean-English-translator mentioned on GitHubtfSyntology: 1 sample, 1 ran (1 instrument-failed) · 0 unverified report
2023-MindSpore-1/ms-code-5 mindsporeSyntology: not harvested report
MindSpore-paper-code-3/code9 mindsporeSyntology: not harvested report
NVIDIA/DeepLearningExamples pytorchSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to 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) and HiFi-GAN: Generative Adversarial Networks for Efficient and High Fidelity Speech Synthesis (arXiv:2010.05646; that paper's own run record: 17 ran (of which 11 constructed an object rather than computing a result; 14 with no instrument failure: 0 honoured, 0 violated, 14 with no contract checked; 3 where Syntology's instrument failed) · 8 unverified); nothing checks that they implement this paper's method. report
cui0523/Code6 mindsporeSyntology: not harvested report
dmlc/gluon-nlp mxnetApache-2.0Syntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to GluonCV and GluonNLP: Deep Learning in Computer Vision and Natural Language Processing (arXiv:1907.04433; 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) · 0 unverified); nothing checks that they implement this paper's method. report
mindspore-ai/models mindsporeSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to AdaBin: Improving Binary Neural Networks with Adaptive Binary Sets (arXiv:2208.08084; that paper's own run record: 4 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 0 where Syntology's instrument failed) · 1 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

46 samples harvested: 34 ran (of which 4 constructed an object rather than computing a result; 25 with no instrument failure: 1 honoured, 2 violated, 22 with no contract checked; 9 where Syntology's instrument failed) · 12 unverified. “Where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. Syntology's record for this page last changed ; when this build read Syntology's graph is in the build record. That date is not when the samples ran.

1ran · honoured contract
2ran · violated contract
9ran · our draft was wrong
22ran
12unverified

Licence: 13 of the 46 samples are pointer only, meaning Syntology does not serve that copy's text. For 1 of them, this paper's copy is under a permissive licence and cleared, but the stored copy of the same code that Syntology serves is not; the licence label's tooltip gives Syntology's recorded reason. This page shows no code text for any sample; each one links to its file in the repository.

Harvested from 7 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. “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”. For 1 sample that ran, the graph records a signature this page does not show: for a class the fixture built without calling, the harness called the object with inputs it made up itself, so the recorded signature is the harness's probe, not the fixture's arguments. “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.

Liut2016/stackedResBiLSTM community (archive-listed) 5 samples, 1 ran (1 instrument-failed) · 4 unverified
relu_fc lstm_architecture.py ran · our draft was wrong Apache-2.0 (permissive) · c8d5e6a10689e5b6 · report fixture: signature input_2D_tensor_list:list/1/EagerTensor, features_len:int/0/int, new_features_len:int/0/int, config:Config/0/? · returned list · level recorded 2026-09-22
batch_norm in 46 papers lstm_architecture.py unverified Apache-2.0 (permissive) · a30358b17cf7f25f · report
bi_LSTM_cell lstm_architecture.py unverified Apache-2.0 (permissive) · 3847ef05ef574aca · report
residual_bidirectional_LSTM_layers lstm_architecture.py unverified Apache-2.0 (permissive) · c39c0d4e280c8846 · report
single_LSTM_cell lstm_architecture.py unverified Apache-2.0 (permissive) · 317abb01a23f7133 · report
ZHANG45/multi_gpu_seq2seq community (archive-listed) 6 samples, 5 ran (0 instrument-failed) · 1 unverified
Decoder in 210 papers seq2seq2.py ran · metamorphic tier: deterministic no licence file found · pointer only · 1657da8312de365d · report fixture: returned Decoder · level recorded 2026-09-22
Encoder in 278 papers seq2seq2.py ran · metamorphic tier: deterministic no licence file found · pointer only · 50db89833b87dbe3 · report fixture: returned Encoder · level recorded 2026-09-22
Generator in 95 papers seq2seq2.py ran · metamorphic tier: deterministic no licence file found · pointer only · 0094511a1c6f0800 · report fixture: returned Generator · level recorded 2026-09-22
Seq2Seq in 6 papers seq2seq2.py ran · metamorphic tier: deterministic no licence file found · pointer only · 92bf320d3ebcecdb · report fixture: returned Seq2Seq · level recorded 2026-09-22
_inverse_indices seq2seq2.py ran · violated contract no licence file found · pointer only · b9cb323bd3d025b6 · report fixture: signature indices:Tensor/1/int · returned ndarray · level recorded 2026-09-22
Attention in 344 papers
census: 13 implementations from 12 papers, 10 distinct outputs across 4 buckets, one shared input per bucket
seq2seq2.py unverified no licence file found · pointer only · e60bd6d0b1cb5dc5 · report
guillaume-chevalier/HAR-stacked-residual-bidir-LSTMs community (archive-listed) 2 samples, 1 ran (0 instrument-failed) · 1 unverified
norm_shape sliding_window.py ran fingerprinted Apache-2.0 (permissive) · 2b8a63bd4c5ab5e4 · report fixture: signature shape:int/0/int · returned tuple · level recorded 2026-09-26
sliding_window in 10 papers sliding_window.py unverified Apache-2.0 (permissive) · ffb489e2974384e9 · report
kh-kim/simple-nmt community (archive-listed) 5 samples, 3 ran (0 instrument-failed) · 2 unverified
Attention in 344 papers
census: 13 implementations from 12 papers, 10 distinct outputs across 4 buckets, one shared input per bucket
simple_nmt/models/seq2seq.py ran · metamorphic tier: invariant no licence file found · pointer only · efc311adeb93a786 · report fixture: returned Tensor · level recorded 2026-09-22
Encoder in 278 papers simple_nmt/models/seq2seq.py ran no licence file found · pointer only · 2662a03f14c86a67 · report fixture: signature emb:tuple/1/Tensor · returned tuple · level recorded 2026-09-24
Generator in 95 papers simple_nmt/models/seq2seq.py ran no licence file found · pointer only · f7231b6041ba6ab3 · report fixture: signature x:Tensor/3/float · returned Tensor · level recorded 2026-09-24
Decoder in 210 papers simple_nmt/models/seq2seq.py unverified no licence file found · pointer only · 5a04587ca39fc628 · report
Seq2Seq in 6 papers simple_nmt/models/seq2seq.py unverified no licence file found · pointer only · 14b02b13476db551 · report
microsoft/BlingFire community (archive-listed) 13 samples, 11 ran (2 instrument-failed) · 2 unverified
convert_to_unicode in 40 papers ldbsrc/bert_base_tok/tokenization.py ran · our draft was wrong fingerprinted MIT (permissive) here; the stored copy is pointer only · 1923fc05163d207d · report fixture: signature text:str/0/str · returned str · level recorded 2026-09-22
is_bert_chinese ldbsrc/bert_multi_cased/generate_letters_from_vocab.py ran MIT (permissive) · 74356079aa5fa20e · report fixture: signature l:str/0/str · returned bool · level recorded 2026-09-25
is_letter ldbsrc/bert_multi_cased/generate_letters_from_vocab.py ran MIT (permissive) · a02d7706aacf6eee · report fixture: signature l:str/0/str · returned bool · level recorded 2026-09-25
my_hex ldbsrc/bert_multi_cased/generate_letters_from_vocab.py ran fingerprinted MIT (permissive) · 0297d56cefe7364c · report fixture: signature i:int/0/int · returned str · level recorded 2026-09-25
parse_range in 22 papers ldbsrc/bert_base_tok/range_minus.py ran fingerprinted MIT (permissive) · 6e673eab8521b6e5 · report fixture: signature s:str/0/str · returned list · level recorded 2026-09-25
parse_range in 22 papers ldbsrc/bert_multi_cased/regexrangeparse.py ran fingerprinted MIT (permissive) · 0ab68692161c1470 · report fixture: signature s:str/0/str · returned list · level recorded 2026-09-25
printable_text in 36 papers ldbsrc/bert_base_tok/tokenization.py ran · our draft was wrong MIT (permissive) · 0e5615f8994003cf · report fixture: signature text:str/0/str · returned str · level recorded 2026-09-26
serialize_range ldbsrc/bert_base_tok/range_minus.py ran MIT (permissive) · 4ef5a73a2f158b4e · report fixture: signature r:ndarray/1/int · returned str · level recorded 2026-09-25
serialize_range ldbsrc/bert_multi_cased/regexrangeparse.py ran MIT (permissive) · 1355f61e60faddd2 · report fixture: signature r:ndarray/1/int · returned str · level recorded 2026-09-25
subtract_range ldbsrc/bert_base_tok/range_minus.py ran MIT (permissive) · 4293ac7fb9af9f5a · report fixture: signature r:list/1/int, minus_r:list/1/int · returned list · level recorded 2026-09-25
subtract_range ldbsrc/bert_multi_cased/regexrangeparse.py ran MIT (permissive) · c1e5731a39dcacd5 · report fixture: signature r:list/1/int, minus_r:list/1/int · returned list · level recorded 2026-09-25
load_vocab in 107 papers ldbsrc/bert_base_tok/tokenization.py unverified MIT (permissive) · ff83ccc8b0b6462d · report
token2regexp ldbsrc/bert_base_cased_tok/vocab_to_fa_lex.py unverified MIT (permissive) · ff133510dfb28e8a · report
psunlpgroup/xsemplr community (archive-listed) 14 samples, 12 ran (5 instrument-failed) · 2 unverified
AverageSpanExtractor model/seq2seqPTR/src/ptrbert.py ran fingerprinted MIT (permissive) · 95b1f6bdad5fb67b · report fixture: signature sequence_tensor:Tensor/3/float, span_indices:Tensor/3/int, span_indices_mask:NoneType/0/? · returned Tensor · level recorded 2026-09-24
BeamSearchNode model/seq2seqPTR/src/ptrbert.py ran fingerprinted MIT (permissive) · 229cf6fba4062cd9 · report fixture: signature alpha:float/0/float · returned float · level recorded 2026-09-24
Generator in 95 papers model/seq2seqPTR/src/ptrbert.py ran · metamorphic tier: invariant MIT (permissive) · 78edbd2119371df3 · report fixture: returned Tensor · level recorded 2026-09-22
LabelSmoothing model/seq2seqPTR/src/ptrbert.py ran · metamorphic tier: invariant MIT (permissive) · 73e4f0852349e7bc · report fixture: signature x:Tensor/2/float, target:Tensor/1/int · returned Tensor · level recorded 2026-09-22
SimpleLossCompute model/seq2seqPTR/src/ptrbert.py ran · metamorphic tier: invariant MIT (permissive) · 1475ad8d2eb28cde · report fixture: signature x:Tensor/3/float, y:Tensor/2/int, norm:Tensor/1/float · returned Tensor · level recorded 2026-09-22
attention in 144 papers
census: 11 implementations from 10 papers, 7 distinct outputs across 5 buckets, one shared input per bucket
model/seq2seqPTR/src/ptrbert.py ran · our draft was wrong MIT (permissive) · 51522955ae4c222d · report fixture: signature query:Tensor/3/float, key:Tensor/3/float, value:Tensor/3/float, mask:Tensor/3/float, dropout:callable/0/? · returned tuple · level recorded 2026-09-22
batched_index_select in 44 papers model/seq2seqPTR/src/ptrbert.py ran · our draft was wrong MIT (permissive) · a2dd9c360300df18 · report fixture: signature target:Tensor/3/float, indices:Tensor/2/int, flattened_indices:NoneType/0/? · returned Tensor · level recorded 2026-09-22
flatten_and_batch_shift_indices model/seq2seqPTR/src/ptrbert.py ran · our draft was wrong fingerprinted MIT (permissive) · aacb87756629bdb1 · report fixture: signature indices:Tensor/2/int, sequence_length:int/0/int · returned Tensor · level recorded 2026-09-22
get_range_vector model/seq2seqPTR/src/ptrbert.py ran · honoured contract MIT (permissive) · 68cef9d2b09ab819 · report fixture: signature size:int/0/int, device:device/0/? · returned Tensor · level recorded 2026-09-22
masked_softmax in 51 papers
census: 10 implementations from 10 papers, 10 distinct outputs across 6 buckets, one shared input per bucket this sample: bucket 1 of 6, arg 1: rank 2, kind float, dtype float32 · arg 2: rank 2, kind float, dtype float32
model/seq2seqPTR/src/ptrbert.py ran · our draft was wrong MIT (permissive) · 42fb56ded96dd10a · report fixture: signature vector:Tensor/2/float, mask:Tensor/2/float, dim:int/0/int, mask_fill_value:float/0/float · returned Tensor · level recorded 2026-09-22
subsequent_mask in 38 papers model/seq2seqPTR/src/ptrbert.py ran · violated contract fingerprinted MIT (permissive) · 2d9b2960c6f86b29 · report fixture: signature size:int/0/int, batch_size:int/0/int · returned Tensor · level recorded 2026-09-22
weighted_sum in 11 papers model/seq2seqPTR/src/ptrbert.py ran · our draft was wrong fingerprinted MIT (permissive) · d3a5188111b2f502 · report fixture: signature matrix:Tensor/3/float, attention:Tensor/2/float · returned Tensor · level recorded 2026-09-22
PtrBART model/seq2seqPTR/src/ptrbert.py unverified MIT (permissive) · b896419ba0888f61 · report
beam_decode_spider model/seq2seqPTR/src/ptrbert.py unverified MIT (permissive) · 9adcd571f14c4937 · report
virsagothethird/Korean-English-translator community (archive-listed) 1 sample, 1 ran (1 instrument-failed) · 0 unverified
define_model in 5 papers src/helpme_spa.py ran · our draft was wrong no licence file found · pointer only · cb8ba397b1c9bfd6 · report fixture: signature src_vocab:int/0/int, tar_vocab:int/0/int, src_timesteps:int/0/int, tar_timesteps:int/0/int, n_units:int/0/int · returned Sequential · level recorded 2026-09-22

Method as code Syntology

What Syntology's graph records as this paper's claimed method, lifted into code: each assembly names its bricks (functions and classes), each with its own role and its own verification level. An assembly is not a check that the code implements the method correctly or reproduces the paper's results. Levels are each brick's own verification level in Syntology's graph (level 0: no recorded run), listed brick by brick and never combined into one level; “ran” means the brick executed on a synthesized input, not that its output is correct, and the instrument figure counts failures of Syntology's instrument, not of the code. Where a model read the code against the paper's claim, each assembly's label verdict is one model's judgement, kept in this page's JSON twin; it is not calibrated, so no card prints it. Siblings are assemblies lifted from this paper in the same batch for the same method: alternative readings kept side by side; none replaces or supersedes another.

5 assemblies on this paper: 5 harvested, 0 generated, listed in 1 groups (siblings lifted in one batch form one group).

5 sibling assemblies for GNMT (harvested), lifted in the same batch on 2026-09-09: alternative readings kept side by side; none replaces or supersedes another.

harvested Assembly for GNMT (graph method: GNMT). 6 bricks; individually on a fixture: 5 ran (of which 4 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 1 violated, 4 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified. The assembly has not been run end-to-end.

one of 5 siblings

  1. Seq2Seq entry · level 1 · ran · 92bf320d3ebcecdb
  2. Decoder model · level 1 · ran · 1657da8312de365d
  3. Encoder model · level 1 · ran · 50db89833b87dbe3
  4. Generator model · level 1 · ran · 0094511a1c6f0800
  5. Attention model · level 0 · unverified · e60bd6d0b1cb5dc5
  6. _inverse_indices helper · level 1 · ran · violated contract · b9cb323bd3d025b6

harvested Assembly for GNMT (graph method: GNMT). 5 bricks; individually on a fixture: 1 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 4 unverified. The assembly has not been run end-to-end.

one of 5 siblings

  1. residual_bidirectional_LSTM_layers entry · level 0 · unverified · c39c0d4e280c8846
  2. batch_norm helper · level 0 · unverified · a30358b17cf7f25f
  3. bi_LSTM_cell model · level 0 · unverified · 3847ef05ef574aca
  4. relu_fc model · level 1 · ran · our draft was wrong · c8d5e6a10689e5b6
  5. single_LSTM_cell helper · level 0 · unverified · 317abb01a23f7133

harvested Assembly for GNMT (graph method: GNMT). 1 brick; individually on a fixture: 1 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified. The assembly has not been run end-to-end.

one of 5 siblings

  1. define_model entry · level 1 · ran · our draft was wrong · cb8ba397b1c9bfd6

harvested Assembly for GNMT (graph method: GNMT). 14 bricks; individually on a fixture: 12 ran (of which 0 constructed an object rather than computing a result; 7 with no instrument failure: 1 honoured, 1 violated, 5 with no contract checked; 5 where Syntology's instrument failed) · 2 unverified. The assembly has not been run end-to-end.

one of 5 siblings

  1. PtrBART entry · level 0 · unverified · b896419ba0888f61
  2. AverageSpanExtractor helper · level 1 · ran · 95b1f6bdad5fb67b
  3. Generator helper · level 1 · ran · 78edbd2119371df3
  4. LabelSmoothing helper · level 1 · ran · 73e4f0852349e7bc
  5. SimpleLossCompute helper · level 1 · ran · 1475ad8d2eb28cde
  6. beam_decode_spider helper · level 0 · unverified · 9adcd571f14c4937
  7. batched_index_select helper · level 1 · ran · our draft was wrong · a2dd9c360300df18
  8. flatten_and_batch_shift_indices helper · level 1 · ran · our draft was wrong · aacb87756629bdb1
  9. get_range_vector helper · level 1 · ran · honoured contract · 68cef9d2b09ab819
  10. masked_softmax helper · level 1 · ran · our draft was wrong · 42fb56ded96dd10a
  11. weighted_sum helper · level 1 · ran · our draft was wrong · d3a5188111b2f502
  12. BeamSearchNode helper · level 1 · ran · 229cf6fba4062cd9
  13. subsequent_mask helper · level 1 · ran · violated contract · 2d9b2960c6f86b29
  14. attention helper · level 1 · ran · our draft was wrong · 51522955ae4c222d

harvested Assembly for GNMT (graph method: GNMT). 6 bricks; individually on a fixture: 3 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 0 where Syntology's instrument failed) · 3 unverified. The assembly has not been run end-to-end.

one of 5 siblings

  1. Seq2Seq entry · level 0 · unverified · 14b02b13476db551
  2. Attention model · level 1 · ran · efc311adeb93a786
  3. Decoder model · level 0 · unverified · 5a04587ca39fc628
  4. Encoder model · level 1 · ran · 2662a03f14c86a67
  5. Generator model · level 1 · ran · f7231b6041ba6ab3
  6. SingleBeamSearchBoard helper · level 0 · unverified · e4c7830c7e8e7867

Each brick ends with its code_sha256, Syntology's identity for that exact code; click one to copy the get_code call that returns it. For agents, on Syntology's MCP service: assembly(arxiv_id="1609.08144") returns these assemblies with each brick's role and wiring (how to connect).

Tasks

DecoderMachine TranslationNMTSentenceTranslation

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Machine Translation WMT2014 English-French GNMT+RL BLEU score 39.9 #36 of 57 Archive leaderboard report
Machine Translation WMT2014 English-French GNMT+RL Hardware Burden 279G #36 of 57 Archive leaderboard report
Machine Translation WMT2014 English-German GNMT+RL BLEU score 26.3 #61 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

LSTMSPEEDSigmoid ActivationTanh ActivationWordPiece

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