Papers › Unsupervised Statistical Machine Translation
Unsupervised Statistical Machine Translation
Mikel Artetxe, Gorka Labaka, Eneko Agirre
While modern machine translation has relied on large parallel corpora, a recent line of work has managed to train Neural Machine Translation (NMT) systems from monolingual corpora only (Artetxe et al., 2018c; Lample et al., 2018). Despite the potential of this approach for low-resource settings, existing systems are far behind their supervised counterparts, limiting their practical interest. In this paper, we propose an alternative approach based on phrase-based Statistical Machine Translation (SMT) that significantly closes the gap with supervised systems. Our method profits from the modular architecture of SMT: we first induce a phrase table from monolingual corpora through cross-lingual embedding mappings, combine it with an n-gram language model, and fine-tune hyperparameters through an unsupervised MERT variant. In addition, iterative backtranslation improves results further, yielding, for instance, 14.08 and 26.22 BLEU points in WMT 2014 English-German and English-French, respectively, an improvement of more than 7-10 BLEU points over previous unsupervised systems, and closing the gap with supervised SMT (Moses trained on Europarl) down to 2-5 BLEU points. Our implementation is available at https://github.com/artetxem/monoses
In Syntology Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.
Code
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
Results from the paper archive 2025-07-28
| Task | Dataset | Model | Metric | Value | Rank at snapshot | Leaderboard | Report |
|---|---|---|---|---|---|---|---|
| Machine Translation | WMT2014 English-French | SMT + iterative backtranslation (unsupervised) | BLEU score | 26.22 | #55 of 57 | Archive leaderboard | report |
| Machine Translation | WMT2014 English-German | SMT + iterative backtranslation (unsupervised) | BLEU score | 14.08 | #88 of 91 | Archive leaderboard | report |
| Machine Translation | WMT2014 French-English | SMT + iterative backtranslation (unsupervised) | BLEU score | 25.87 | #3 of 3 | Archive leaderboard | report |
| Machine Translation | WMT2014 German-English | SMT + iterative backtranslation (unsupervised) | BLEU score | 17.43 | #16 of 16 | Archive leaderboard | report |
| Machine Translation | WMT2016 English-German | SMT + iterative backtranslation (unsupervised) | BLEU score | 18.23 | #9 of 12 | Archive leaderboard | report |
| Machine Translation | WMT2016 German-English | SMT + iterative backtranslation (unsupervised) | BLEU score | 23.05 | #5 of 8 | Archive leaderboard | report |
| Unsupervised Machine Translation | WMT2014 French-English | SMT | BLEU | 25.9 | #7 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