Unsupervised Machine Translation
Unsupervised machine translation is the task of doing machine translation without any translation resources at training time.
State-of-the-art leaderboards
| Trend | Dataset | Best Method | Paper title | Paper | Code | Compare |
|---|---|---|---|---|---|---|
|
||||||
|
||||||
|
||||||
|
||||||
|
||||||
|
||||||
|
||||||
|
||||||
|
Latest papers with code
MASS: Masked Sequence to Sequence Pre-training for Language Generation
• microsoft/MASS
• 
Pre-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.
SOTA for Text Summarization on GigaWord
TEXT GENERATION TEXT SUMMARIZATION UNSUPERVISED MACHINE TRANSLATION
Cross-lingual Language Model Pretraining
• huggingface/pytorch-pretrained-BERT
•
On unsupervised machine translation, we obtain 34. 3 BLEU on WMT'16 German-English, improving the previous state of the art by more than 9 BLEU.
Unsupervised Neural Machine Translation with SMT as Posterior Regularization
To address this issue, we introduce phrase based Statistic Machine Translation (SMT) models which are robust to noisy data, as posterior regularizations to guide the training of unsupervised NMT models in the iterative back-translation process.
#2 best model for
Unsupervised Machine Translation
on WMT2014 English-German
Unsupervised Statistical Machine Translation
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).
Phrase-Based & Neural Unsupervised Machine Translation
EMNLP 2018
• facebookresearch/XLM
•
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 to the majority of language pairs.
#2 best model for
Machine Translation
on WMT2016 English-Russian
Unsupervised Machine Translation Using Monolingual Corpora Only
ICLR 2018
• facebookresearch/MUSE
•
By learning to reconstruct in both languages from this shared feature space, the model effectively learns to translate without using any labeled data.
#5 best model for
Machine Translation
on WMT2016 German-English
Unsupervised Neural Machine Translation
ICLR 2018 • rsennrich/subword-nmt
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.
#6 best model for
Machine Translation
on WMT2015 English-German
Word Translation Without Parallel Data
ICLR 2018
• facebookresearch/MUSE
•
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.
SOTA for Word Alignment on en-es
UNSUPERVISED MACHINE TRANSLATION WORD ALIGNMENT WORD EMBEDDINGS