Browse SoTA > Natural Language Processing > Machine Translation > Unsupervised Machine Translation

Unsupervised Machine Translation

19 papers with code · Natural Language Processing
Subtask of Machine Translation

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

Greatest papers with code

Multilingual Denoising Pre-training for Neural Machine Translation

22 Jan 2020huggingface/transformers

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

DENOISING UNSUPERVISED MACHINE TRANSLATION

Cross-lingual Language Model Pretraining

NeurIPS 2019 huggingface/transformers

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 NATURAL LANGUAGE UNDERSTANDING UNSUPERVISED MACHINE TRANSLATION

Phrase-Based & Neural Unsupervised Machine Translation

EMNLP 2018 huggingface/transformers

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.

UNSUPERVISED MACHINE TRANSLATION

Cross-lingual Retrieval for Iterative Self-Supervised Training

NeurIPS 2020 pytorch/fairseq

Recent studies have demonstrated the cross-lingual alignment ability of multilingual pretrained language models.

UNSUPERVISED MACHINE TRANSLATION

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.

UNSUPERVISED MACHINE TRANSLATION

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.

UNSUPERVISED MACHINE TRANSLATION WORD ALIGNMENT WORD EMBEDDINGS

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.

UNSUPERVISED MACHINE TRANSLATION

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

7 May 2019microsoft/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.

CONVERSATIONAL RESPONSE GENERATION TEXT GENERATION TEXT SUMMARIZATION UNSUPERVISED MACHINE TRANSLATION

Unsupervised Translation of Programming Languages

NeurIPS 2020 facebookresearch/TransCoder

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.

UNSUPERVISED MACHINE TRANSLATION