Unsupervised Machine Translation

Description from the archive archive 2025-07-28.

Benchmarks archive 2025-07-28

9 leaderboard tables shown for this task, 9 with rows (a “benchmark” on this site is a table with at least one row, as on /sota), ordered by row count. “Best model” is the first row in the archive's own order at snapshot; nothing is re-ranked here and metric direction is not recorded in the archive. PwC's Trend sparklines are not in the archive, so that column is omitted.

Syntology column: samples harvested from the paper's repositories and executed on synthesized fixtures; “ran” is not a correctness claim and does not order the table. A dash means no Syntology record for that paper, not a recorded non-run. Read from the graph 2026-09-24.

Libraries

Not in the archive: the export carries no per-task library table, so there is nothing to show at snapshot 2025-07-28.

Datasets archive 2025-07-28

4 datasets whose archive record lists this task, ordered by the archive's paper count.

Subtasks archive 2025-07-28

No subtask under this task in the archive's task tree.

Parent tasks archive 2025-07-28

Most implemented papers archive 2025-07-28

30 shown of 33 papers with code (102 tagged with this task in all), ordered by repositories listed in the archive, not by stars (the archive holds no stars, so PwC's “Social” and “Latest” sorts cannot be reproduced). Papers without a page here are shown as plain text.

• Language Models are Few-Shot Learners
  28 May 2020 67 repositories listed Syntology ran 15 of 65 samples · 50 unverified · 4 pointer-only (licence)
  By contrast, humans can generally perform a new language task from only a few examples or from simple instructions - something which current NLP systems still largely struggle to do.
• Word Translation Without Parallel Data
  11 Oct 2017 20 repositories listed Syntology ran 6 of 8 samples · 2 unverified · 8 pointer-only (licence)
  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…
• Cross-lingual Language Model Pretraining
  22 Jan 2019 17 repositories listed Syntology ran 1 of 7 samples · 6 unverified · 1 pointer-only (licence)
  On unsupervised machine translation, we obtain 34.
• Phrase-Based & Neural Unsupervised Machine Translation
  20 Apr 2018 14 repositories listed
  Machine translation systems achieve near human-level performance on some languages, yet their effectiveness strongly relies on the availability of large amounts of parallel sentences, which hinders their applicability…
• Unsupervised Machine Translation Using Monolingual Corpora Only
  31 Oct 2017 14 repositories listed Syntology ran 3 of 14 samples · 11 unverified · 5 pointer-only (licence)
  By learning to reconstruct in both languages from this shared feature space, the model effectively learns to translate without using any labeled data.
• Unsupervised Translation of Programming Languages
  5 Jun 2020 9 repositories listed Syntology ran 1 of 8 samples · 7 unverified
  We train our model on source code from open source GitHub projects, and show that it can translate functions between C++, Java, and Python with high accuracy.
• Multilingual Denoising Pre-training for Neural Machine Translation
  22 Jan 2020 8 repositories listed
  This paper demonstrates that multilingual denoising pre-training produces significant performance gains across a wide variety of machine translation (MT) tasks.
• MASS: Masked Sequence to Sequence Pre-training for Language Generation
  7 May 2019 7 repositories listed
  Pre-training and fine-tuning, e.
• A Probabilistic Formulation of Unsupervised Text Style Transfer
  10 Feb 2020 5 repositories listed Syntology ran 18 of 25 samples · 7 unverified · 12 pointer-only (licence)
  Across all style transfer tasks, our approach yields substantial gains over state-of-the-art non-generative baselines, including the state-of-the-art unsupervised machine translation techniques that our approach…
• Incorporating BERT into Neural Machine Translation
  17 Feb 2020 3 repositories listed
  While BERT is more commonly used as fine-tuning instead of contextual embedding for downstream language understanding tasks, in NMT, our preliminary exploration of using BERT as contextual embedding is better than using…
• Unsupervised Statistical Machine Translation
  4 Sep 2018 3 repositories listed
  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…
• Unsupervised Neural Machine Translation
  30 Oct 2017 2 repositories listed Syntology ran 6 of 6 samples · 0 unverified · 6 pointer-only (licence)
  In spite of the recent success of neural machine translation (NMT) in standard benchmarks, the lack of large parallel corpora poses a major practical problem for many language pairs.
• Quick Back-Translation for Unsupervised Machine Translation
  1 Dec 2023 1 repository listed
  The field of unsupervised machine translation has seen significant advancement from the marriage of the Transformer and the back-translation algorithm.
• Weakly-supervised Deep Cognate Detection Framework for Low-Resourced Languages Using Morphological Knowledge of Closely-Related Languages
  9 Nov 2023 1 repository listed
  We train an encoder to gain morphological knowledge of a language and transfer the knowledge to perform unsupervised and weakly-supervised cognate detection tasks with and without the pivot language for the…
• Bilex Rx: Lexical Data Augmentation for Massively Multilingual Machine Translation
  27 Mar 2023 1 repository listed
  Neural machine translation (NMT) has progressed rapidly over the past several years, and modern models are able to achieve relatively high quality using only monolingual text data, an approach dubbed Unsupervised…
• Unsupervised Mandarin-Cantonese Machine Translation
  10 Jan 2023 1 repository listed
  Advancements in unsupervised machine translation have enabled the development of machine translation systems that can translate between languages for which there is not an abundance of parallel data available.
• A Theory of Unsupervised Translation Motivated by Understanding Animal Communication
  20 Nov 2022 1 repository listed
  Neural networks are capable of translating between languages -- in some cases even between two languages where there is little or no access to parallel translations, in what is known as Unsupervised Machine Translation…
• Refining Low-Resource Unsupervised Translation by Language Disentanglement of Multilingual Model
  31 May 2022 1 repository listed Syntology ran 2 of 2 samples · 0 unverified
  Numerous recent work on unsupervised machine translation (UMT) implies that competent unsupervised translations of low-resource and unrelated languages, such as Nepali or Sinhala, are only possible if the model is…
• Leveraging Automated Unit Tests for Unsupervised Code Translation
  13 Oct 2021 1 repository listed
  With little to no parallel data available for programming languages, unsupervised methods are well-suited to source code translation.
• Unsupervised Translation of German--Lower Sorbian: Exploring Training and Novel Transfer Methods on a Low-Resource Language
  24 Sep 2021 1 repository listed
  Lastly, we experiment with the order in which offline and online back-translation are used to train an unsupervised system, finding that using online back-translation first works better for DE→DSB by 2.
• Break-It-Fix-It: Unsupervised Learning for Program Repair
  11 Jun 2021 1 repository listed Syntology ran 0 of 6 samples · 6 unverified
  To bridge this gap, we propose a new training approach, Break-It-Fix-It (BIFI), which has two key ideas: (i) we use the critic to check a fixer's output on real bad inputs and add good (fixed) outputs to the training…
• Zero-Shot Language Transfer vs Iterative Back Translation for Unsupervised Machine Translation
  31 Mar 2021 1 repository listed
  This work focuses on comparing different solutions for machine translation on low resource language pairs, namely, with zero-shot transfer learning and unsupervised machine translation.
• Low-Resource Unsupervised NMT: Diagnosing the Problem and Providing a Linguistically Motivated Solution
  1 Nov 2020 1 repository listed
  Unsupervised Machine Translation has been advancing our ability to translate without parallel data, but state-of-the-art methods assume an abundance of monolingual data.
• The LMU Munich System for the WMT 2020 Unsupervised Machine Translation Shared Task
  25 Oct 2020 1 repository listed
  Our core unsupervised neural machine translation (UNMT) system follows the strategy of Chronopoulou et al.
• Unsupervised Vision-and-Language Pre-training Without Parallel Images and Captions
  24 Oct 2020 1 repository listed Syntology ran 3 of 3 samples · 0 unverified · 3 pointer-only (licence)
  Pre-trained contextual vision-and-language (V&L) models have achieved impressive performance on various benchmarks.
• A Retrieve-and-Rewrite Initialization Method for Unsupervised Machine Translation
  1 Jul 2020 1 repository listed
  The commonly used framework for unsupervised machine translation builds initial translation models of both translation directions, and then performs iterative back-translation to jointly boost their translation…
• Cross-lingual Retrieval for Iterative Self-Supervised Training
  16 Jun 2020 1 repository listed
  Recent studies have demonstrated the cross-lingual alignment ability of multilingual pretrained language models.
• Cross-model Back-translated Distillation for Unsupervised Machine Translation
  3 Jun 2020 1 repository listed
  Recent unsupervised machine translation (UMT) systems usually employ three main principles: initialization, language modeling and iterative back-translation, though they may apply them differently.
• Unsupervised Multilingual Alignment using Wasserstein Barycenter
  28 Jan 2020 1 repository listed
  We study unsupervised multilingual alignment, the problem of finding word-to-word translations between multiple languages without using any parallel data.
• Generating Classical Chinese Poems from Vernacular Chinese
  31 Aug 2019 1 repository listed
  According to experiments, our approach significantly improve the perplexity and BLEU compared with typical UMT models.

Syntology lines on 10 of the papers shown; no Syntology record for the others (a paper without an arXiv id cannot be joined to the graph, and absence from the graph layer is not a recorded non-run). “Ran” means the sample executed on a synthesized fixture, not that the paper's result was reproduced. Read from the graph 2026-09-24.