SOTAVerified

Unsupervised 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 )

Papers

Showing 76100 of 102 papers

TitleStatusHype
NICT's Unsupervised Neural and Statistical Machine Translation Systems for the WMT19 News Translation Task0
The LMU Munich Unsupervised Machine Translation System for WMT190
Bilingual Lexicon Induction through Unsupervised Machine TranslationCode0
Unsupervised Joint Training of Bilingual Word Embeddings0
Translating Translationese: A Two-Step Approach to Unsupervised Machine Translation0
Generalized Data Augmentation for Low-Resource Translation0
Machine Translation With Weakly Paired Bilingual Documents0
Bilingual-GAN: A Step Towards Parallel Text Generation0
Extract and Edit: An Alternative to Back-Translation for Unsupervised Neural Machine Translation0
EAT: a simple and versatile semantic representation format for multi-purpose NLP0
An Effective Approach to Unsupervised Machine TranslationCode0
Cross-lingual Language Model PretrainingCode0
Unsupervised Neural Machine Translation with SMT as Posterior RegularizationCode0
Off-the-Shelf Unsupervised NMT0
Unsupervised Neural Machine Translation Initialized by Unsupervised Statistical Machine Translation0
The LMU Munich Unsupervised Machine Translation Systems0
LMU Munich's Neural Machine Translation Systems at WMT 20180
Phrase-based Unsupervised Machine Translation with Compositional Phrase Embeddings0
Phrase-Based \& Neural Unsupervised Machine Translation0
Style Transfer as Unsupervised Machine Translation0
Orthographic Features for Bilingual Lexicon Induction0
On the Limitations of Unsupervised Bilingual Dictionary Induction0
Phrase-Based & Neural Unsupervised Machine TranslationCode0
Generative Models for Alignment and Data Efficiency in Language0
Unsupervised Machine Translation Using Monolingual Corpora OnlyCode0
Show:102550
← PrevPage 4 of 5Next →

No leaderboard results yet.