Papers › Unsupervised Machine Translation Using Monolingual Corpora Only

Unsupervised Machine Translation Using Monolingual Corpora Only

31 Oct 2017ICLR 2018 1arXiv:1711.00043archive 2025-07-28

Guillaume Lample, Alexis Conneau, Ludovic Denoyer, Marc'Aurelio Ranzato

Machine translation has recently achieved impressive performance thanks to recent advances in deep learning and the availability of large-scale parallel corpora. There have been numerous attempts to extend these successes to low-resource language pairs, yet requiring tens of thousands of parallel sentences. In this work, we take this research direction to the extreme and investigate whether it is possible to learn to translate even without any parallel data. We propose a model that takes sentences from monolingual corpora in two different languages and maps them into the same latent space. By learning to reconstruct in both languages from this shared feature space, the model effectively learns to translate without using any labeled data. We demonstrate our model on two widely used datasets and two language pairs, reporting BLEU scores of 32.8 and 15.1 on the Multi30k and WMT English-French datasets, without using even a single parallel sentence at training time.

PaperPDFConference PDFCodeCode Syntology ran

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

For agents, Syntology's MCP tool lists every function and class Syntology harvested from this paper and whether it ran (how to connect): get_harvested_code_for_paper(arxiv_id="1711.00043")

Code

Syntology Ran 3 of 14 code samples harvested from 3 repositories linked to this paper; 11 have no recorded run. Of those that ran: 1 ran · violated contract; 1 ran · our draft was wrong; 1 ran · fixture could not drive it.

By repository: community (archive-listed): 14 samples from 3 repositories, 3 ran. The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

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

Babylonpartners/MultilingualFactorAnalysis mentioned on GitHubpytorchApache-2.0 report
YovaKem/generalized-procrustes-MUSE mentioned on GitHubpytorchNOASSERTION report
babylonhealth/MultilingualFactorAnalysis mentioned on GitHubpytorchApache-2.0 report
barnerwothers/MUSE mentioned on GitHubpytorch report
facebookresearch/MUSE mentioned on GitHubpytorch report
freedombenLiu/MUSE mentioned on GitHubpytorchNOASSERTION report
jiajunhua/facebookresearch-MUSE mentioned on GitHubpytorchNOASSERTION report
keleog/PidginUNMT mentioned on GitHubpytorch report
labdac/charlacompling mentioned on GitHub report
makozi/AfrikaansNMT mentioned on GitHub report
maochf/MUSE mentioned on GitHubpytorchNOASSERTION report
migonch/unsupervised_mt mentioned on GitHubpytorch report
sabetAI/bucc-eval mentioned on GitHubpytorchNOASSERTION report
samnguyen8991/Facebook-MUSE mentioned on GitHubpytorchNOASSERTION report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

14 samples harvested; 3 ran; 0 honoured the contract we drafted; 11 have no recorded run. Read from Syntology's graph 2026-09-24; that is when this build read the record, not when the samples ran.

1ran · violated contract
1ran · our draft was wrong
1ran · fixture could not drive it
11unverified

Licence: 5 of the 14 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 3 repositories linked to this paper, official or community; each sample names its own and says which. “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. “Honoured” and “violated” refer to a contract Syntology drafted from the code itself; “our draft was wrong” and “fixture could not drive it” are failures of Syntology's instrument, not of the code.

Each sample ends with its code_sha256, Syntology's identity for that exact code. An agent fetches the stored sample with Syntology's MCP tool get_code(code_sha256="…") (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 from a repository marked official are listed first. 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 four 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; or the licence is outside the permissive list Syntology serves text under (MIT, Apache-2.0, BSD and similar). 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.

chunk barnerwothers/MUSE/src/alignment_functions.py community (archive-listed) ran · our draft was wrong fingerprinted licence not identified · pointer only · 40cdf0f2f7b382ee · report
init_with_browne barnerwothers/MUSE/src/alignment_functions.py community (archive-listed) ran · fixture could not drive it licence not identified · pointer only · a1dac87bef6453c3 · report
nll_FA barnerwothers/MUSE/src/alignment_functions.py community (archive-listed) ran · violated contract fingerprinted licence not identified · pointer only · 9f9b17d2052bad0d · report
bow Babylonpartners/MultilingualFactorAnalysis/src/utils.py community (archive-listed) unverified Apache-2.0 (permissive) · 1017986b046fa3e5 · report
build_dictionary Babylonpartners/MultilingualFactorAnalysis/src/dico_builder.py community (archive-listed) unverified Apache-2.0 (permissive) · 0a6749c257608531 · report
build_model Babylonpartners/MultilingualFactorAnalysis/src/models.py community (archive-listed) unverified Apache-2.0 (permissive) · 420c0f482a285b84 · report
build_seq2seq_model keleog/PidginUNMT/src/model/seq2seq.py community (archive-listed) unverified licence not identified · pointer only · 095dc5970a2bfba9 · report
create_logger Babylonpartners/MultilingualFactorAnalysis/src/logger.py community (archive-listed) unverified Apache-2.0 (permissive) · 00b78a626a078a5b · report
get_candidates Babylonpartners/MultilingualFactorAnalysis/src/dico_builder.py community (archive-listed) unverified Apache-2.0 (permissive) · 069588d6ca04276f · report
get_init_state keleog/PidginUNMT/src/model/seq2seq.py community (archive-listed) unverified licence not identified · pointer only · 32cc6430b851519d · report
initialize_exp Babylonpartners/MultilingualFactorAnalysis/src/utils.py community (archive-listed) unverified Apache-2.0 (permissive) · 21a3d4ec06ede4eb · report
load_fasttext_model Babylonpartners/MultilingualFactorAnalysis/src/utils.py community (archive-listed) unverified Apache-2.0 (permissive) · 2b93faa3b4ec4872 · report
read_dict Babylonpartners/MultilingualFactorAnalysis/create_embeddings.py community (archive-listed) unverified Apache-2.0 (permissive) · b68d645b4c6b0a2a · report
sample_language_pair Babylonpartners/MultilingualFactorAnalysis/create_embeddings.py community (archive-listed) unverified Apache-2.0 (permissive) · affe0a63af29c7b1 · report

Tasks

Machine TranslationSentenceTranslationUnsupervised Machine Translation

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Machine Translation WMT2016 English-German Unsupervised S2S with attention BLEU score 9.64 #11 of 12 Archive leaderboard report
Machine Translation WMT2016 German-English Unsupervised S2S with attention BLEU score 13.33 #7 of 8 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.

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