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 )
|TREND||DATASET||BEST METHOD||PAPER TITLE||PAPER||CODE||COMPARE|
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.
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
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
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
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.
SOTA for Language Modelling on Penn Treebank (Word Level) (using extra training data)
COMMON SENSE REASONING COREFERENCE RESOLUTION DOMAIN ADAPTATION FEW-SHOT LEARNING LANGUAGE MODELLING NATURAL LANGUAGE INFERENCE QUESTION ANSWERING SENTENCE COMPLETION UNSUPERVISED MACHINE TRANSLATION WORD SENSE DISAMBIGUATION
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
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.
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).
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.
#4 best model for Machine Translation on WMT2014 English-German