Papers › An Effective Approach to Unsupervised Machine Translation

An Effective Approach to Unsupervised Machine Translation

4 Feb 2019ACL 2019 7arXiv:1902.01313archive 2025-07-28

Mikel Artetxe, Gorka Labaka, Eneko Agirre

While machine translation has traditionally relied on large amounts of parallel corpora, a recent research line has managed to train both Neural Machine Translation (NMT) and Statistical Machine Translation (SMT) systems using monolingual corpora only. In this paper, we identify and address several deficiencies of existing unsupervised SMT approaches by exploiting subword information, developing a theoretically well founded unsupervised tuning method, and incorporating a joint refinement procedure. Moreover, we use our improved SMT system to initialize a dual NMT model, which is further fine-tuned through on-the-fly back-translation. Together, we obtain large improvements over the previous state-of-the-art in unsupervised machine translation. For instance, we get 22.5 BLEU points in English-to-German WMT 2014, 5.5 points more than the previous best unsupervised system, and 0.5 points more than the (supervised) shared task winner back in 2014.

PaperPDFConference PDFCode

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

Code

artetxem/monoses officialmentioned in paperpytorchGPL-3.0 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

Not run by Syntology. Nothing on this page verifies that the listed code works.

Tasks

Machine TranslationNMTTranslationUnsupervised Machine Translation

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Unsupervised Machine Translation WMT2014 English-French SMT + NMT (tuning and joint refinement) BLEU 36.2 #3 of 7 Archive leaderboard report
Unsupervised Machine Translation WMT2014 English-German SMT + NMT (tuning and joint refinement) BLEU 22.5 #1 of 2 Archive leaderboard report
Unsupervised Machine Translation WMT2014 French-English SMT + NMT (tuning and joint refinement) BLEU 33.5 #3 of 7 Archive leaderboard report
Unsupervised Machine Translation WMT2014 German-English SMT + NMT (tuning and joint refinement) BLEU 27.0 #1 of 2 Archive leaderboard report
Unsupervised Machine Translation WMT2016 English-German SMT + NMT (tuning and joint refinement) BLEU 26.9 #3 of 7 Archive leaderboard report
Unsupervised Machine Translation WMT2016 German-English SMT + NMT (tuning and joint refinement) BLEU 34.4 #3 of 7 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