Unsupervised Machine Translation
32 papers with code • 9 benchmarks • 4 datasets
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 )
Benchmarks
These leaderboards are used to track progress in Unsupervised Machine Translation
| Trend | Dataset | Best Model | Paper | Code | Compare |
|---|---|---|---|---|---|
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
|||||
|
Libraries
Use these libraries to find Unsupervised Machine Translation models and implementations
WMT 2014
WMT 2016
CCMatrix
WMT 2016 News
Latest papers
Unsupervised Vision-and-Language Pre-training Without Parallel Images and Captions
uclanlp/visualbert
•
•
NAACL 2021
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
Imagist-Shuo/RRforUNMT
•
•
ACL 2020
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 performance.
Cross-lingual Retrieval for Iterative Self-Supervised Training
pytorch/fairseq
•
•
NeurIPS 2020
Recent studies have demonstrated the cross-lingual alignment ability of multilingual pretrained language models.
Unsupervised Translation of Programming Languages
facebookresearch/TransCoder
•
•
NeurIPS 2020
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.
Cross-model Back-translated Distillation for Unsupervised Machine Translation
nxphi47/multiagent_crosstranslate
•
•
Recent unsupervised machine translation (UMT) systems usually employ three main principles: initialization, language modeling and iterative back-translation, though they may apply them differently.
Language Models are Few-Shot Learners
ggerganov/llama.cpp
•
•
NeurIPS 2020
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.
Incorporating BERT into Neural Machine Translation
bert-nmt/bert-nmt
•
•
ICLR 2020
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 for fine-tuning.
A Probabilistic Formulation of Unsupervised Text Style Transfer
martiansideofthemoon/style-transfer-paraphrase
•
•
ICLR 2020
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 generalizes.
Unsupervised Multilingual Alignment using Wasserstein Barycenter
We study unsupervised multilingual alignment, the problem of finding word-to-word translations between multiple languages without using any parallel data.
Multilingual Denoising Pre-training for Neural Machine Translation
This paper demonstrates that multilingual denoising pre-training produces significant performance gains across a wide variety of machine translation (MT) tasks.
