Papers › Effective Approaches to Attention-based Neural Machine Translation

Effective Approaches to Attention-based Neural Machine Translation

17 Aug 2015EMNLP 2015 9arXiv:1508.04025archive 2025-07-28

Minh-Thang Luong, Hieu Pham, Christopher D. Manning

An attentional mechanism has lately been used to improve neural machine translation (NMT) by selectively focusing on parts of the source sentence during translation. However, there has been little work exploring useful architectures for attention-based NMT. This paper examines two simple and effective classes of attentional mechanism: a global approach which always attends to all source words and a local one that only looks at a subset of source words at a time. We demonstrate the effectiveness of both approaches over the WMT translation tasks between English and German in both directions. With local attention, we achieve a significant gain of 5.0 BLEU points over non-attentional systems which already incorporate known techniques such as dropout. Our ensemble model using different attention architectures has established a new state-of-the-art result in the WMT'15 English to German translation task with 25.9 BLEU points, an improvement of 1.0 BLEU points over the existing best system backed by NMT and an n-gram reranker.

PaperPDFConference PDFCodeCode 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 8 code samples harvested from 2 repositories linked to this paper: 7 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 1 honoured, 0 violated, 5 with no contract checked; 1 where Syntology's instrument failed) · 1 unverified. Where Syntology's instrument failed: 1 where our contract draft was wrong; failures of Syntology's instrument, not of the code.

By repository: community (archive-listed): 8 samples from 2 repositories, 7 ran (6 with no instrument failure; 1 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 7 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.

44 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
CongBao/ChatBot mentioned on GitHubSyntology: not harvested report
DorinK/Assignment-2-Neural-Machine-Translation mentioned on GitHubpytorchSyntology: not harvested report
KevinYoung98/Seq2Seq-PyTorch mentioned on GitHubpytorchSyntology: not harvested report
Pendulibrium/ai-visual-storytelling-seq2seq mentioned on GitHubtfSyntology: not harvested 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
T9-LIN/MSc-Project mentioned on GitHubpytorchSyntology: not harvested report
amitz25/PCCoder mentioned on GitHubpytorchSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to RobustFill: Neural Program Learning under Noisy I/O (arXiv:1703.07469; that paper's own run record: 5 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; 2 where Syntology's instrument failed) · 3 unverified); nothing checks that they implement this paper's method. report
b-etienne/Seq2seq-PyTorch mentioned on GitHubpytorchSyntology: not harvested report
biyoml/End-to-End-Mandarin-ASR mentioned on GitHubpytorchSyntology: not harvested report
biyoml/Pytorch-End-to-End-ASR-on-TIMIT mentioned on GitHubpytorchSyntology: not harvested report
bplank/teaching-dl4nlp mentioned on GitHubSyntology: not harvested report
chao-ji/tf-seq2seq mentioned on GitHubtfSyntology: not harvested report
dalek7/attention mentioned on GitHubtfSyntology: not harvested report
eaplatanios/symphony-mt mentioned on GitHubtfApache-2.0Syntology: not harvested report
fqyshelly/CS224n-Winter2019-assignment-solutions mentioned on GitHubpytorchSyntology: not harvested report
hnt4499/seq2seq mentioned on GitHubpytorchSyntology: 2 samples, 2 ran (1 instrument-failed) · 0 unverified report
huulinhcvp/chatBot mentioned on GitHubpytorchSyntology: not harvested report
jackjhliu/End-to-End-Mandarin-ASR mentioned on GitHubpytorchSyntology: not harvested report
jackjhliu/Pytorch-End-to-End-ASR-on-TIMIT mentioned on GitHubpytorchSyntology: not harvested report
jmyrberg/finnlem mentioned on GitHubtfSyntology: not harvested report
khanhptnk/bandit-nmt mentioned on GitHubpytorchSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Asynchronous Methods for Deep Reinforcement Learning (arXiv:1602.01783; that paper's own run record: 60 ran (of which 20 constructed an object rather than computing a result; 50 with no instrument failure: 2 honoured, 1 violated, 47 with no contract checked; 10 where Syntology's instrument failed) · 35 unverified); nothing checks that they implement this paper's method. report
ldulcic/chatbot mentioned on GitHubpytorchSyntology: not harvested report
mike-a-yen/date-translation mentioned on GitHubpytorchSyntology: not harvested report
neqkir/attention-mechanism mentioned on GitHubtfSyntology: not harvested report
pbcquoc/transformer mentioned on GitHubSyntology: not harvested report
pcyin/pytorch_basic_nmt mentioned on GitHubpytorchSyntology: not harvested report
philipperemy/keras-attention-mechanism mentioned on GitHubtfApache-2.0Syntology: not harvested report
prachetaphadnis/NMT_Seq2Seq_LexicalModel mentioned on GitHubpytorchMITSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Improving Lexical Choice in Neural Machine Translation (arXiv:1710.01329; that paper's own run record: 5 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; 0 where Syntology's instrument failed) · 4 unverified); nothing checks that they implement this paper's method. report
riversdie/chatbot mentioned on GitHubpytorchApache-2.0Syntology: 6 samples, 5 ran (0 instrument-failed) · 1 unverified report
saisandeep97/Chat-botV2 mentioned on GitHubpytorchSyntology: not harvested report
say2sarwar/DeepAcid mentioned on GitHubSyntology: not harvested report
sblayush/Tensorflow-Attention mentioned on GitHubtfSyntology: not harvested report
sblayush/summarization mentioned on GitHubtfSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Get To The Point: Summarization with Pointer-Generator Networks (arXiv:1704.04368; that paper's own run record: 30 ran (of which 11 constructed an object rather than computing a result; 25 with no instrument failure: 4 honoured, 2 violated, 19 with no contract checked; 5 where Syntology's instrument failed) · 34 unverified); nothing checks that they implement this paper's method. report
sen-pai/audio-word2vec-pytorch mentioned on GitHubpytorchSyntology: not harvested report
shlokmehrotra/Convocare mentioned on GitHubpytorchSyntology: not harvested report
sooftware/attentions mentioned on GitHubpytorchMITSyntology: 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
kh-kim/simple-nmt pytorchSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Google's Neural Machine Translation System: Bridging the Gap between Human and Machine... (arXiv:1609.08144; that paper's own run record: 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) and 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
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

8 samples harvested: 7 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 1 honoured, 0 violated, 5 with no contract checked; 1 where Syntology's instrument failed) · 1 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.

1ran · honoured contract
1ran · our draft was wrong
5ran
1unverified

Licence: 2 of the 8 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 2 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. 2 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.

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
riversdie/chatbot community (archive-listed) 6 samples, 5 ran (0 instrument-failed) · 1 unverified
binaryMatrix dataload.py ran Apache-2.0 (permissive) · b6b872f7d5584b69 · report fixture: signature l:list/1/list, value:int/0/int · returned list · level recorded 2026-09-26
create_collate_fn dataload.py ran Apache-2.0 (permissive) · 7cb03e0b055a9dc9 · report fixture: signature padding:int/0/int, eos:int/0/int · returned function · level recorded 2026-09-26
generate in 143 papers
census: 5 implementations from 6 papers, 5 distinct outputs across 4 buckets, one shared input per bucket
train_eval.py ran Apache-2.0 (permissive) · d69ad61c90b8b0e6 · report fixture: signature input_seq:list/1/int, searcher:callable/0/?, sos:int/0/int, eos:int/0/int, opt:Options/0/? · returned Tensor · level recorded 2026-09-26
maskNLLLoss train_eval.py ran Apache-2.0 (permissive) · 191c9a860107527f · report fixture: signature inp:Tensor/2/float, target:Tensor/1/int, mask:Tensor/1/bool · returned tuple · level recorded 2026-09-26
zeroPadding dataload.py ran Apache-2.0 (permissive) · ca2ca3da0d6d55cf · report fixture: signature l:list/1/list, fillvalue:int/0/int · returned list · level recorded 2026-09-26
train_by_batch train_eval.py unverified Apache-2.0 (permissive) · 7b6afaedcd708676 · report

Tasks

Image-guided Story Ending GenerationMachine TranslationNMTSentenceTranslation

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Image-guided Story Ending Generation LSMDC-E Seq2Seq BLEU-1 14.21 #4 of 4 Archive leaderboard report
Image-guided Story Ending Generation LSMDC-E Seq2Seq BLEU-2 4.56 #4 of 4 Archive leaderboard report
Image-guided Story Ending Generation LSMDC-E Seq2Seq BLEU-3 1.70 #4 of 4 Archive leaderboard report
Image-guided Story Ending Generation LSMDC-E Seq2Seq BLEU-4 0.70 #4 of 4 Archive leaderboard report
Image-guided Story Ending Generation LSMDC-E Seq2Seq CIDEr 8.69 #4 of 4 Archive leaderboard report
Image-guided Story Ending Generation LSMDC-E Seq2Seq METEOR 11.01 #4 of 4 Archive leaderboard report
Image-guided Story Ending Generation LSMDC-E Seq2Seq ROUGE-L 19.69 #4 of 4 Archive leaderboard report
Image-guided Story Ending Generation VIST-E Seq2Seq BLEU-1 13.96 #6 of 6 Archive leaderboard report
Image-guided Story Ending Generation VIST-E Seq2Seq BLEU-2 5.57 #6 of 6 Archive leaderboard report
Image-guided Story Ending Generation VIST-E Seq2Seq BLEU-3 2.94 #6 of 6 Archive leaderboard report
Image-guided Story Ending Generation VIST-E Seq2Seq BLEU-4 1.69 #6 of 6 Archive leaderboard report
Image-guided Story Ending Generation VIST-E Seq2Seq CIDEr 12.04 #6 of 6 Archive leaderboard report
Image-guided Story Ending Generation VIST-E Seq2Seq METEOR 4.54 #6 of 6 Archive leaderboard report
Image-guided Story Ending Generation VIST-E Seq2Seq ROUGE-L 16.84 #6 of 6 Archive leaderboard report
Machine Translation 20NEWS 12 Accuracy 1.0 #2 of 2 Archive leaderboard report
Machine Translation WMT2014 English-German RNN Enc-Dec Att BLEU score 20.9 #76 of 91 Archive leaderboard report
Machine Translation WMT2014 English-German Reverse RNN Enc-Dec BLEU score 14.0 #89 of 91 Archive leaderboard report
Machine Translation WMT2014 English-German RNN Enc-Dec BLEU score 11.3 #90 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

Location-based AttentionMultiplicative AttentionSoftmax

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