Papers › Word Translation Without Parallel Data

Word Translation Without Parallel Data

11 Oct 2017ICLR 2018 1arXiv:1710.04087archive 2025-07-28

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

State-of-the-art methods for learning cross-lingual word embeddings have relied on bilingual dictionaries or parallel corpora. Recent studies showed that the need for parallel data supervision can be alleviated with character-level information. While these methods showed encouraging results, they are not on par with their supervised counterparts and are limited to pairs of languages sharing a common alphabet. In this work, we show that we can build a bilingual dictionary between two languages without using any parallel corpora, by aligning monolingual word embedding spaces in an unsupervised way. Without using any character information, our model even outperforms existing supervised methods on cross-lingual tasks for some language pairs. Our experiments demonstrate that our method works very well also for distant language pairs, like English-Russian or English-Chinese. We finally describe experiments on the English-Esperanto low-resource language pair, on which there only exists a limited amount of parallel data, to show the potential impact of our method in fully unsupervised machine translation. Our code, embeddings and dictionaries are publicly available.

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="1710.04087")

Code

Syntology Ran 6 of 8 code samples harvested from 1 repository linked to this paper; 2 have no recorded run. Of those that ran: 2 ran · violated contract; 3 ran · our draft was wrong; 1 ran · fixture could not drive it.

By repository: community (archive-listed): 5 samples from 1 repository, 3 ran; 3 identical to code first harvested elsewhere. The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

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

facebookresearch/MUSE officialmentioned in papermentioned on GitHubpytorch report
AlexMoreo/funnelling mentioned on GitHub report
Babylonpartners/MultilingualFactorAnalysis mentioned on GitHubpytorchApache-2.0 report
YovaKem/generalized-procrustes-MUSE mentioned on GitHubpytorchNOASSERTION report
andreapdr/gfun mentioned on GitHubpytorchGPL-3.0 report
babylonhealth/MultilingualFactorAnalysis mentioned on GitHubpytorchApache-2.0 report
baidu-research/HNN mentioned on GitHub report
barnerwothers/MUSE mentioned on GitHubpytorch report
beinborn/SemanticDrift mentioned on GitHubpytorchGPL-3.0 report
freedombenLiu/MUSE mentioned on GitHubpytorchNOASSERTION report
jiajunhua/facebookresearch-MUSE mentioned on GitHubpytorchNOASSERTION report
labdac/charlacompling mentioned on GitHub report
maochf/MUSE mentioned on GitHubpytorchNOASSERTION report
sabetAI/bucc-eval mentioned on GitHubpytorchNOASSERTION report
samnguyen8991/Facebook-MUSE mentioned on GitHubpytorchNOASSERTION report
yunsukim86/wbw-lm mentioned on GitHubpytorch report
zzzxiaohong/icbt mentioned on GitHubpytorch report

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

Code Syntology ran Syntology

8 samples harvested; 6 ran; 0 honoured the contract we drafted; 2 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.

2ran · violated contract
3ran · our draft was wrong
1ran · fixture could not drive it
2unverified

Licence: 8 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 yunsukim86/wbw-lm. Some samples are identical code Syntology first harvested from another repository; for those, this paper's copy is not located and its licence is not recorded. “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.

get_candidates yunsukim86/wbw-lm/src/dico_builder.py community (archive-listed) ran · our draft was wrong licence not identified · pointer only · 43adfe189ff205a7 · report
is_zip yunsukim86/wbw-lm/translate.py community (archive-listed) ran · violated contract licence not identified · pointer only · 5beb538fcaf76383 · report
open_file yunsukim86/wbw-lm/translate.py community (archive-listed) ran · our draft was wrong fingerprinted licence not identified · pointer only · 0e698708dcb2aac8 · report
build_dictionary yunsukim86/wbw-lm/src/dico_builder.py community (archive-listed) unverified licence not identified · pointer only · 4ed787d9444bb493 · report
load_input yunsukim86/wbw-lm/translate.py community (archive-listed) unverified licence not identified · pointer only · 052e782956f7ae75 · report
chunk identical code first harvested elsewhere ran · our draft was wrong fingerprinted licence of this copy not recorded · 40cdf0f2f7b382ee · report
init_with_browne identical code first harvested elsewhere ran · fixture could not drive it licence of this copy not recorded · a1dac87bef6453c3 · report
nll_FA identical code first harvested elsewhere ran · violated contract fingerprinted licence of this copy not recorded · 9f9b17d2052bad0d · report

Tasks

Cross-Lingual Word EmbeddingsMachine TranslationTranslationUnsupervised Machine TranslationWord AlignmentWord EmbeddingsWord Translation

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Word Alignment en-es Adv - Refine - CSLS P@1 81.7 #2 of 2 Archive leaderboard report
Word Alignment en-fr Adv - Refine - CSLS P@1 82.3 #2 of 2 Archive leaderboard report
Word Alignment es-en Adv - Refine - CSLS P@1 83.3 #2 of 2 Archive leaderboard report
Word Alignment fr-en Adv - Refine - CSLS P@1 82.1 #2 of 2 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