Browse State-of-the-Art › Unsupervised Machine Translation
Unsupervised Machine Translation
33 papers with code · 9 benchmarks · 4 datasets archive 2025-07-28
Unsupervised machine translation is the task of doing machine translation without any translation resources at training time.
( Image credit: Phrase-Based & Neural 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 1 newer paper was judged to report on this task's benchmarks so far (Claude Sonnet 4.5, reading their tables: a model's judgement, not a result; 0 placed): WMT2014 German-English (1 judged, 0 placed). Drawn from 8,886 of 18,637 newer papers checked so far (733 more had nothing to place; 41 could not be read).
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. Each line reads “N ran (of which C constructed an object rather than computing a result; K with no instrument failure: H honoured, V violated, P with no contract checked; I where Syntology's instrument failed) · U unverified”; the instrument figure counts failures of Syntology's instrument, not of the code. When the archive marks a repository official for the row's paper, the line starts with that repository's state (“official” is the archive's flag, not a verdict on who wrote the code; “community repositories only” when every sample that ran came from a community repository, “official: no sample here; runs from other or unrecorded repositories” when some came from a repository the paper names or has in its text, or from none recorded); hover it for the repositories the samples that ran came from. A dash means no Syntology record for that paper, not a recorded non-run. Each “ran” line links to that paper's sample list. Syntology's record for this page last changed ; when this build read Syntology's graph is in the build record. For agents: get_harvested_code_for_paper(arxiv_id) lists each paper's samples; how to connect.
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
Papers archive 2025-07-28
archive papers tagged: 102 · with a code link: 33 · where Syntology ran a sample: 11 (11 with a run with no instrument failure, 0 where every run was a failure of Syntology's instrument) Syntology
Show: all tagged papersonly where code ran (11 of 102 tagged: 11 with a run with no instrument failure, 0 where every run was a failure of Syntology's instrument)
Page 1 of 2: papers 1 to 100 of 102, in archive order: by repositories listed in the archive (most first), then newest first, not by stars (the archive holds no stars, so PwC's “Social” and “Latest” sorts cannot be reproduced). Papers that list no repository come after every paper that lists one.
Papers without a page here are shown as plain text. A Syntology line reads “N ran (of which C constructed an object rather than computing a result; K with no instrument failure: H honoured, V violated, P with no contract checked; I where Syntology's instrument failed) · U unverified”; the figure “where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. When the archive marks a repository official for the paper, the line starts with that repository's state (the archive's flag, not a verdict on who wrote the code); hover it for the repositories the samples that ran came from. The first sentence of the abstract is shown for the first 30 papers; every abstract is on its paper's page.
-
28 May 2020 67 repositories listed Syntology community repositories only · 45 ran (of which 0 constructed an object rather than computing a result; 37 with no instrument failure: 3 honoured, 2 violated, 32 with no contract checked; 8 where Syntology's instrument failed) · 20 unverified (of 65 harvested samples) · 7 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.
-
11 Oct 2017 20 repositories listed Syntology community repositories only · 6 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 2 violated, 0 with no contract checked; 4 where Syntology's instrument failed) · 2 unverified (of 8 harvested samples) · 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…
-
22 Jan 2019 17 repositories listed Syntology 5 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 1 violated, 4 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified (of 7 harvested samples) · 1 pointer-only (licence)On unsupervised machine translation, we obtain 34.
-
20 Apr 2018 14 repositories listedMachine 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…
-
31 Oct 2017 14 repositories listed Syntology 7 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 1 violated, 4 with no contract checked; 2 where Syntology's instrument failed) · 7 unverified (of 14 harvested samples) · 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.
-
5 Jun 2020 9 repositories listed Syntology community repositories only · 7 ran (of which 0 constructed an object rather than computing a result; 7 with no instrument failure: 0 honoured, 1 violated, 6 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified (of 8 harvested samples)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.
-
22 Jan 2020 8 repositories listedThis paper demonstrates that multilingual denoising pre-training produces significant performance gains across a wide variety of machine translation (MT) tasks.
-
7 May 2019 7 repositories listedPre-training and fine-tuning, e. g., BERT, have achieved great success in language understanding by transferring knowledge from rich-resource pre-training task to the low/zero-resource downstream tasks.
-
10 Feb 2020 5 repositories listed Syntology official: no sample here; runs from other or unrecorded repositories · 18 ran (of which 13 constructed an object rather than computing a result; 11 with no instrument failure: 0 honoured, 0 violated, 11 with no contract checked; 7 where Syntology's instrument failed) · 7 unverified (of 25 harvested samples) · 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…
-
17 Feb 2020 3 repositories listedWhile 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…
-
4 Sep 2018 3 repositories listedWhile 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…
-
30 Oct 2017 2 repositories listed Syntology official (archive's flag): 6 ran · 6 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 1 violated, 0 with no contract checked; 5 where Syntology's instrument failed) · 0 unverified (of 6 harvested samples) · 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.
-
1 Dec 2023 1 repository listedThe field of unsupervised machine translation has seen significant advancement from the marriage of the Transformer and the back-translation algorithm.
-
9 Nov 2023 1 repository listedWe 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…
-
27 Mar 2023 1 repository listedNeural 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…
-
10 Jan 2023 1 repository listedAdvancements 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.
-
20 Nov 2022 1 repository listedNeural 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…
-
31 May 2022 1 repository listed Syntology official (archive's flag): 2 ran · 2 ran (of which 1 constructed an object rather than computing a result; 2 with no instrument failure: 1 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified (of 2 harvested samples)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…
-
13 Oct 2021 1 repository listedWith little to no parallel data available for programming languages, unsupervised methods are well-suited to source code translation.
-
24 Sep 2021 1 repository listedLastly, 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.
-
11 Jun 2021 1 repository listed Syntology official (archive's flag): 6 ran · 6 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 0 honoured, 0 violated, 6 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified (of 6 harvested samples)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…
-
31 Mar 2021 1 repository listedThis work focuses on comparing different solutions for machine translation on low resource language pairs, namely, with zero-shot transfer learning and unsupervised machine translation.
-
1 Nov 2020 1 repository listedUnsupervised Machine Translation has been advancing our ability to translate without parallel data, but state-of-the-art methods assume an abundance of monolingual data.
-
25 Oct 2020 1 repository listedOur core unsupervised neural machine translation (UNMT) system follows the strategy of Chronopoulou et al. (2020), using a monolingual pretrained language generation model (on German) and fine-tuning it on both German…
-
24 Oct 2020 1 repository listed Syntology 3 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 2 where Syntology's instrument failed) · 0 unverified (of 3 harvested samples) · 3 pointer-only (licence)Pre-trained contextual vision-and-language (V&L) models have achieved impressive performance on various benchmarks.
-
1 Jul 2020 1 repository listedThe 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…
-
16 Jun 2020 1 repository listedRecent studies have demonstrated the cross-lingual alignment ability of multilingual pretrained language models.
-
3 Jun 2020 1 repository listedRecent unsupervised machine translation (UMT) systems usually employ three main principles: initialization, language modeling and iterative back-translation, though they may apply them differently.
-
28 Jan 2020 1 repository listedWe study unsupervised multilingual alignment, the problem of finding word-to-word translations between multiple languages without using any parallel data.
-
31 Aug 2019 1 repository listedAccording to experiments, our approach significantly improve the perplexity and BLEU compared with typical UMT models.
-
24 Jul 2019 1 repository listed
-
4 Feb 2019 1 repository listed
-
14 Jan 2019 1 repository listed Syntology official (archive's flag): 7 ran · 7 ran (of which 0 constructed an object rather than computing a result; 7 with no instrument failure: 0 honoured, 0 violated, 7 with no contract checked; 0 where Syntology's instrument failed) · 8 unverified (of 15 harvested samples)
-
Effective Self-Mining of In-Context Examples for Unsupervised Machine Translation with LLMs14 Oct 2024 0 repositories listed
-
Decoupled Vocabulary Learning Enables Zero-Shot Translation from Unseen Languages5 Aug 2024 0 repositories listed
-
The Impact of Syntactic and Semantic Proximity on Machine Translation with Back-Translation26 Mar 2024 0 repositories listed
-
Boosting Unsupervised Machine Translation with Pseudo-Parallel Data22 Oct 2023 0 repositories listed
-
On the Role of Parallel Data in Cross-lingual Transfer Learning20 Dec 2022 0 repositories listed
-
Domain Mismatch Doesn't Always Prevent Cross-Lingual Transfer Learning30 Nov 2022 0 repositories listed
-
CUNI Submission to MT4All Shared Task1 Jun 2022 0 repositories listed
-
Domain Mismatch Doesn’t Always Prevent Cross-lingual Transfer Learning1 Jun 2022 0 repositories listed
-
Unsupervised Machine Translation in Real-World Scenarios1 Jun 2022 0 repositories listed
-
QiuNiu: A Chinese Lyrics Generation System with Passage-Level Input1 May 2022 0 repositories listed
-
Flow-Adapter Architecture for Unsupervised Machine Translation26 Apr 2022 0 repositories listed
-
On Systematic Style Differences between Unsupervised and Supervised MT and an Application for High-Resource Machine Translation16 Nov 2021 0 repositories listed
-
Unsupervised Neural Machine Translation with Universal Grammar1 Nov 2021 0 repositories listed
-
Unsupervised Translation of German–Lower Sorbian: Exploring Training and Novel Transfer Methods on a Low-Resource Language1 Nov 2021 0 repositories listed
-
Multilingual Unsupervised Neural Machine Translation with Denoising Adapters20 Oct 2021 0 repositories listed
-
Contrastive Clustering to Mine Pseudo Parallel Data for Unsupervised Translation29 Sep 2021 0 repositories listed
-
Translating Robot Skills: Learning Unsupervised Skill Correspondences Across Robots29 Sep 2021 0 repositories listed
-
Paraphrase Generation as Unsupervised Machine Translation7 Sep 2021 0 repositories listed
-
Exploring Cross-Lingual Transfer Learning with Unsupervised Machine Translation1 Aug 2021 0 repositories listed
-
Manipuri-English Machine Translation using Comparable Corpus1 Aug 2021 0 repositories listed
-
Integrating Unsupervised Data Generation into Self-Supervised Neural Machine Translation for Low-Resource Languages19 Jul 2021 0 repositories listed
-
On Systematic Style Differences between Unsupervised and Supervised MT and an Application for High-Resource Machine Translation30 Jun 2021 0 repositories listed
-
Crosslingual Embeddings are Essential in UNMT for Distant Languages: An English to IndoAryan Case Study9 Jun 2021 0 repositories listed
-
Unsupervised Multilingual Sentence Embeddings for Parallel Corpus Mining21 May 2021 0 repositories listed
-
Backretrieval: An Image-Pivoted Evaluation Metric for Cross-Lingual Text Representations Without Parallel Corpora11 May 2021 0 repositories listed
-
Efficient Unsupervised NMT for Related Languages with Cross-Lingual Language Models and Fidelity Objectives1 Apr 2021 0 repositories listed
-
Unsupervised Machine Translation On Dravidian Languages29 Mar 2021 0 repositories listed
-
From Unsupervised Machine Translation To Adversarial Text Generation10 Nov 2020 0 repositories listed
-
Data Selection for Unsupervised Translation of German–Upper Sorbian1 Nov 2020 0 repositories listed
-
SJTU-NICT’s Supervised and Unsupervised Neural Machine Translation Systems for the WMT20 News Translation Task1 Nov 2020 0 repositories listed
-
The NITS-CNLP System for the Unsupervised MT Task at WMT 20201 Nov 2020 0 repositories listed
-
UdS-DFKI@WMT20: Unsupervised MT and Very Low Resource Supervised MT for German-Upper Sorbian1 Nov 2020 0 repositories listed
-
Unsupervised Neural Machine Translation for Low-Resource Domains via Meta-Learning18 Oct 2020 0 repositories listed
-
SJTU-NICT's Supervised and Unsupervised Neural Machine Translation Systems for the WMT20 News Translation Task11 Oct 2020 0 repositories listed
-
Harnessing Multilinguality in Unsupervised Machine Translation for Rare Languages23 Sep 2020 0 repositories listed
-
Cross-Lingual Unsupervised Sentiment Classification with Multi-View Transfer Learning1 Jul 2020 0 repositories listed
-
Data Augmentation with Unsupervised Machine Translation Improves the Structural Similarity of Cross-lingual Word Embeddings30 May 2020 0 repositories listed
-
Unsupervised Multimodal Neural Machine Translation with Pseudo Visual Pivoting6 May 2020 0 repositories listed
-
Data-dependent Gaussian Prior Objective for Language Generation1 May 2020 0 repositories listed
-
A Call for More Rigor in Unsupervised Cross-lingual Learning30 Apr 2020 0 repositories listed
-
Semi-Supervised Text Simplification with Back-Translation and Asymmetric Denoising Autoencoders30 Apr 2020 0 repositories listed
-
When Does Unsupervised Machine Translation Work?12 Apr 2020 0 repositories listed
-
Do all Roads Lead to Rome? Understanding the Role of Initialization in Iterative Back-Translation28 Feb 2020 0 repositories listed
-
A Multilingual View of Unsupervised Machine Translation7 Feb 2020 0 repositories listed
-
Comparing Unsupervised Word Translation Methods Step by Step1 Dec 2019 0 repositories listed
-
Machine Translation With Weakly Paired Documents1 Nov 2019 0 repositories listed
-
Supervised and Unsupervised Machine Translation for Myanmar-English and Khmer-English1 Nov 2019 0 repositories listed
-
Study on Unsupervised Statistical Machine Translation for Backtranslation1 Sep 2019 0 repositories listed
-
Explicit Cross-lingual Pre-training for Unsupervised Machine Translation31 Aug 2019 0 repositories listed
-
Incorporating Word and Subword Units in Unsupervised Machine Translation Using Language Model Rescoring16 Aug 2019 0 repositories listed
-
NICT's Unsupervised Neural and Statistical Machine Translation Systems for the WMT19 News Translation Task1 Aug 2019 0 repositories listed
-
The LMU Munich Unsupervised Machine Translation System for WMT191 Aug 2019 0 repositories listed
-
Unsupervised Joint Training of Bilingual Word Embeddings1 Jul 2019 0 repositories listed
-
Translating Translationese: A Two-Step Approach to Unsupervised Machine Translation11 Jun 2019 0 repositories listed
-
Generalized Data Augmentation for Low-Resource Translation10 Jun 2019 0 repositories listed
-
Machine Translation With Weakly Paired Bilingual Documents1 May 2019 0 repositories listed
-
Bilingual-GAN: A Step Towards Parallel Text Generation9 Apr 2019 0 repositories listed
-
Extract and Edit: An Alternative to Back-Translation for Unsupervised Neural Machine Translation4 Apr 2019 0 repositories listed
-
EAT: a simple and versatile semantic representation format for multi-purpose NLP25 Feb 2019 0 repositories listed
-
Off-the-Shelf Unsupervised NMT6 Nov 2018 0 repositories listed
-
30 Oct 2018 0 repositories listed
-
LMU Munich's Neural Machine Translation Systems at WMT 20181 Oct 2018 0 repositories listed
-
Phrase-Based & Neural Unsupervised Machine Translation1 Oct 2018 0 repositories listed
-
Phrase-based Unsupervised Machine Translation with Compositional Phrase Embeddings1 Oct 2018 0 repositories listed
-
The LMU Munich Unsupervised Machine Translation Systems1 Oct 2018 0 repositories listed
-
Style Transfer as Unsupervised Machine Translation23 Aug 2018 0 repositories listed
-
Orthographic Features for Bilingual Lexicon Induction1 Jul 2018 0 repositories listed
Syntology lines on 11 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; each line links to that paper's sample list. Syntology's record for this page last changed ; when this build read Syntology's graph is in the build record. For agents: get_harvested_code_for_paper(arxiv_id) lists each paper's samples; how to connect.
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