Machine Translation on WMT2014 English-French

Metric: BLEU (higher is better)

LeaderboardDataset

Loading chart...

Results

Submit a result

Sort:

#	Model↕	BLEU▼	Extra Data	Paper	Date↕	Code
1	BERT-fused NMT	38.27	No	Incorporating BERT into Neural Machine Translation	2020-02-17	Code
2	MASS (6-layer Transformer)	37.5	No	MASS: Masked Sequence to Sequence Pre-training f...	2019-05-07	Code
3	SMT + NMT (tuning and joint refinement)	36.2	No	An Effective Approach to Unsupervised Machine Tr...	2019-02-04	Code
4	MLM pretraining for encoder and decoder	33.4	No	Cross-lingual Language Model Pretraining	2019-01-22	Code
5	GPT-3 175B (Few-Shot)	32.6	No	Language Models are Few-Shot Learners	2020-05-28	Code
6	SMT as posterior regularization	29.5	No	Unsupervised Neural Machine Translation with SMT...	2019-01-14	Code
7	PBSMT + NMT	27.6	No	Phrase-Based & Neural Unsupervised Machine Trans...	2018-04-20	Code

#1BERT-fused NMTSOTA
38.27
BLEU· 2020-02-17
Incorporating BERT into Neural Machine Translation Code
#2MASS (6-layer Transformer)SOTA
37.5
BLEU· 2019-05-07
MASS: Masked Sequence to Sequence Pre-training for Language Generation Code
#3SMT + NMT (tuning and joint refinement)SOTA
36.2
BLEU· 2019-02-04
An Effective Approach to Unsupervised Machine Translation Code
#4MLM pretraining for encoder and decoderSOTA
33.4
BLEU· 2019-01-22
Cross-lingual Language Model Pretraining Code
#5GPT-3 175B (Few-Shot)
32.6
BLEU· 2020-05-28
Language Models are Few-Shot Learners Code
#6SMT as posterior regularizationSOTA
29.5
BLEU· 2019-01-14
Unsupervised Neural Machine Translation with SMT as Posterior Regularization Code
#7PBSMT + NMTSOTA
27.6
BLEU· 2018-04-20
Phrase-Based & Neural Unsupervised Machine Translation Code