Unsupervised Machine Translation

26 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 )

Greatest papers with code

Multilingual Denoising Pre-training for Neural Machine Translation

huggingface/transformers 22 Jan 2020

This paper demonstrates that multilingual denoising pre-training produces significant performance gains across a wide variety of machine translation (MT) tasks.

Denoising Document-level +2

Cross-lingual Language Model Pretraining

huggingface/transformers NeurIPS 2019

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.

Language Modelling Language understanding +3

Phrase-Based & Neural Unsupervised Machine Translation

huggingface/transformers EMNLP 2018

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.

Translation Unsupervised Machine Translation

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.

Translation Unsupervised Machine Translation

Language Models are Few-Shot Learners

openai/gpt-3 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.

Common Sense Reasoning Coreference Resolution +10

Unsupervised Machine Translation Using Monolingual Corpora Only

facebookresearch/MUSE ICLR 2018

By learning to reconstruct in both languages from this shared feature space, the model effectively learns to translate without using any labeled data.

Translation Unsupervised Machine Translation

Word Translation Without Parallel Data

facebookresearch/MUSE ICLR 2018

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.

Translation Unsupervised Machine Translation +2

Unsupervised Neural Machine Translation

rsennrich/subword-nmt ICLR 2018

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.

Translation Unsupervised Machine Translation

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.

Code Translation Translation +1

MASS: Masked Sequence to Sequence Pre-training for Language Generation

microsoft/MASS 7 May 2019

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.

Conversational Response Generation Fine-tuning +5