Machine Translation on IWSLT2014 German-English

Metric: BLEU score (higher is better)

LeaderboardDataset

Loading chart...

Results

Hide extra data

Sort:

#	Model↕	BLEU score▼	Extra Data	Paper	Date↕	Code
1	PiNMT	40.43	No	Integrating Pre-trained Language Model into Neur...	2023-10-30	-
2	BiBERT	38.61	No	BERT, mBERT, or BiBERT? A Study on Contextualize...	2021-09-09	Code
3	Bi-SimCut	38.37	No	Bi-SimCut: A Simple Strategy for Boosting Neural...	2022-06-06	Code
4	Cutoff + Relaxed Attention + LM	37.96	Yes	Relaxed Attention for Transformer Models	2022-09-20	Code
5	DRDA	37.95	No	Deterministic Reversible Data Augmentation for N...	2024-06-04	Code
6	Transformer + R-Drop + Cutoff	37.9	No	R-Drop: Regularized Dropout for Neural Networks	2021-06-28	Code
7	SimCut	37.81	No	Bi-SimCut: A Simple Strategy for Boosting Neural...	2022-06-06	Code
8	Cutoff+Knee	37.78	No	Wide-minima Density Hypothesis and the Explore-E...	2020-03-09	Code
9	Cutoff	37.6	No	A Simple but Tough-to-Beat Data Augmentation App...	2020-09-29	Code
10	CipherDAug	37.53	No	CipherDAug: Ciphertext based Data Augmentation f...	2022-04-01	Code
11	Transformer + R-Drop	37.25	No	R-Drop: Regularized Dropout for Neural Networks	2021-06-28	Code
12	Data Diversification	37.2	No	Data Diversification: A Simple Strategy For Neur...	2019-11-05	Code
13	UniDrop	36.88	No	UniDrop: A Simple yet Effective Technique to Imp...	2021-04-11	-
14	MixedRepresentations	36.41	No	-	-	Code
15	Mask Attention Network (small)	36.3	No	Mask Attention Networks: Rethinking and Strength...	2021-03-25	Code
16	MUSE(Parallel Multi-scale Attention)	36.3	No	MUSE: Parallel Multi-Scale Attention for Sequenc...	2019-11-17	Code
17	Transformer+Rep(Sim)+WDrop	36.22	No	Rethinking Perturbations in Encoder-Decoders for...	2021-04-05	Code
18	MAT	36.22	No	Multi-branch Attentive Transformer	2020-06-18	Code
19	TransformerBase + AutoDropout	35.8	No	AutoDropout: Learning Dropout Patterns to Regula...	2021-01-05	Code
20	Local Joint Self-attention	35.7	No	Joint Source-Target Self Attention with Locality...	2019-05-16	Code
21	TaLK Convolutions	35.5	No	Time-aware Large Kernel Convolutions	2020-02-08	Code
22	ImitKD + Full	35.4	No	Autoregressive Knowledge Distillation through Im...	2020-09-15	Code
23	DeLighT	35.3	No	DeLighT: Deep and Light-weight Transformer	2020-08-03	Code
24	DynamicConv	35.2	No	Pay Less Attention with Lightweight and Dynamic ...	2019-01-29	Code
25	Transformer	35.1385	No	Guidelines for the Regularization of Gammas in B...	2022-05-15	-
26	LightConv	34.8	No	Pay Less Attention with Lightweight and Dynamic ...	2019-01-29	Code
27	Transformer	34.44	No	Attention Is All You Need	2017-06-12	Code
28	Rfa-Gate-arccos	34.4	No	Random Feature Attention	2021-03-03	-
29	Variational Attention	33.1	No	Latent Alignment and Variational Attention	2018-07-10	Code
30	Minimum Risk Training [Edunov2017]	32.84	No	Classical Structured Prediction Losses for Seque...	2017-11-14	Code
31	CNAT	31.15	No	Non-Autoregressive Translation by Learning Targe...	2021-03-21	Code
32	Neural PBMT + LM [Huang2018]	30.08	No	Towards Neural Phrase-based Machine Translation	2017-06-17	Code
33	Back-Translation Finetuning	28.83	Yes	Tag-less Back-Translation	2019-12-22	-
34	Actor-Critic [Bahdanau2017]	28.53	No	An Actor-Critic Algorithm for Sequence Prediction	2016-07-24	Code

#1PiNMTSOTA
40.43
BLEU score· 2023-10-30
Integrating Pre-trained Language Model into Neural Machine Translation
#2BiBERTSOTA
38.61
BLEU score· 2021-09-09
BERT, mBERT, or BiBERT? A Study on Contextualized Embeddings for Neural Machine Translation Code
#3Bi-SimCut
38.37
BLEU score· 2022-06-06
Bi-SimCut: A Simple Strategy for Boosting Neural Machine Translation Code
#4Cutoff + Relaxed Attention + LM
37.96
BLEU score· Extra Data· 2022-09-20
Relaxed Attention for Transformer Models Code
#5DRDA
37.95
BLEU score· 2024-06-04
Deterministic Reversible Data Augmentation for Neural Machine Translation Code
#6Transformer + R-Drop + CutoffSOTA
37.9
BLEU score· 2021-06-28
R-Drop: Regularized Dropout for Neural Networks Code
#7SimCut
37.81
BLEU score· 2022-06-06
Bi-SimCut: A Simple Strategy for Boosting Neural Machine Translation Code
#8Cutoff+KneeSOTA
37.78
BLEU score· 2020-03-09
Wide-minima Density Hypothesis and the Explore-Exploit Learning Rate Schedule Code
#9Cutoff
37.6
BLEU score· 2020-09-29
A Simple but Tough-to-Beat Data Augmentation Approach for Natural Language Understanding and Generation Code
#10CipherDAug
37.53
BLEU score· 2022-04-01
CipherDAug: Ciphertext based Data Augmentation for Neural Machine Translation Code
#11Transformer + R-Drop
37.25
BLEU score· 2021-06-28
R-Drop: Regularized Dropout for Neural Networks Code
#12Data DiversificationSOTA
37.2
BLEU score· 2019-11-05
Data Diversification: A Simple Strategy For Neural Machine Translation Code
#13UniDrop
36.88
BLEU score· 2021-04-11
UniDrop: A Simple yet Effective Technique to Improve Transformer without Extra Cost
#14MixedRepresentations
36.41
BLEU score
No paperCode
#15Mask Attention Network (small)
36.3
BLEU score· 2021-03-25
Mask Attention Networks: Rethinking and Strengthen Transformer Code
#16MUSE(Parallel Multi-scale Attention)
36.3
BLEU score· 2019-11-17
MUSE: Parallel Multi-Scale Attention for Sequence to Sequence Learning Code
#17Transformer+Rep(Sim)+WDrop
36.22
BLEU score· 2021-04-05
Rethinking Perturbations in Encoder-Decoders for Fast Training Code
#18MAT
36.22
BLEU score· 2020-06-18
Multi-branch Attentive Transformer Code
#19TransformerBase + AutoDropout
35.8
BLEU score· 2021-01-05
AutoDropout: Learning Dropout Patterns to Regularize Deep Networks Code
#20Local Joint Self-attentionSOTA
35.7
BLEU score· 2019-05-16
Joint Source-Target Self Attention with Locality Constraints Code
#21TaLK Convolutions
35.5
BLEU score· 2020-02-08
Time-aware Large Kernel Convolutions Code
#22ImitKD + Full
35.4
BLEU score· 2020-09-15
Autoregressive Knowledge Distillation through Imitation Learning Code
#23DeLighT
35.3
BLEU score· 2020-08-03
DeLighT: Deep and Light-weight Transformer Code
#24DynamicConvSOTA
35.2
BLEU score· 2019-01-29
Pay Less Attention with Lightweight and Dynamic Convolutions Code
#25Transformer
35.1385
BLEU score· 2022-05-15
Guidelines for the Regularization of Gammas in Batch Normalization for Deep Residual Networks
#26LightConv
34.8
BLEU score· 2019-01-29
Pay Less Attention with Lightweight and Dynamic Convolutions Code
#27TransformerSOTA
34.44
BLEU score· 2017-06-12
Attention Is All You Need Code
#28Rfa-Gate-arccos
34.4
BLEU score· 2021-03-03
Random Feature Attention
#29Variational Attention
33.1
BLEU score· 2018-07-10
Latent Alignment and Variational Attention Code
#30Minimum Risk Training [Edunov2017]
32.84
BLEU score· 2017-11-14
Classical Structured Prediction Losses for Sequence to Sequence Learning Code
#31CNAT
31.15
BLEU score· 2021-03-21
Non-Autoregressive Translation by Learning Target Categorical Codes Code
#32Neural PBMT + LM [Huang2018]
30.08
BLEU score· 2017-06-17
Towards Neural Phrase-based Machine Translation Code
#33Back-Translation Finetuning
28.83
BLEU score· Extra Data· 2019-12-22
Tag-less Back-Translation
#34Actor-Critic [Bahdanau2017]SOTA
28.53
BLEU score· 2016-07-24
An Actor-Critic Algorithm for Sequence Prediction Code