Our new X account is live! Follow @wizwand_team for updates

Machine Translation on WMT En-De 2014 (test)

31.69BLEU

Transformer

Updated 3d ago

Evaluation Results

Method
Transformer 2021.03	31.69	-	-	-	-	-	-	-	-	-	-	-	-	-	-
MAT 2020.06	30.8	-	30.2	-	-	-	-	-	-	-	-	-	-	-	-
BERT-fused model 2020.02	30.75	-	-	-	-	-	-	-	-	-	-	-	-	-	-
mRASP 2022.03	30.3	-	-	-	-	-	-	-	-	-	-	-	-	-	-
Transformer (Ott et al., 2018) + LayerDrop 2019.09	30.2	-	-	-	-	-	-	-	-	-	-	-	-	-	-
MAT 2020.06	30.1	-	29.7	-	-	-	-	-	-	-	-	-	-	-	-
MAT 2020.06	30	-	29.6	-	-	-	-	-	-	-	-	-	-	-	-
CeMAT 2022.03	30	-	-	-	-	-	-	-	-	-	-	-	-	-	-
Depth Growing 2019.07	29.92	-	-	-	-	-	-	-	-	-	-	-	-	-	-
MAT 2020.06	29.9	-	29.4	-	-	-	-	-	-	-	-	-	-	-	-
Evolved Transformer 2019.01	29.8	-	29.2	-	-	-	-	-	-	-	-	-	-	-	-
Evolved Transformer 2020.02	29.8	-	-	-	-	-	-	-	-	-	-	-	-	-	-
Transformer 2020.06	29.8	-	29.2	-	-	-	-	-	-	-	-	-	-	-	-
back-translation 2023.06	29.8	-	-	-	-	-	-	-	-	54.3	-	-	-	-	-
Wu et al. (2019) 2019.05	29.7	-	-	-	-	-	-	-	-	-	-	-	-	-	-
Joint Self-attention 2019.05	29.7	-	-	-	-	-	-	-	-	-	-	-	-	-	-
Local Joint Self-attention 2019.05	29.7	-	-	-	-	-	-	-	-	-	-	-	-	-	-
Wu et al. 2019.01	29.7	-	-	-	-	-	-	-	-	-	-	-	-	-	-
DynamicConv (Wu et al., 2019) 2019.09	29.7	-	-	-	-	-	-	-	-	-	-	-	-	-	-
DynamicConv 2020.02	29.7	-	-	-	-	-	-	-	-	-	-	-	-	-	-
Wu et al. 2020.02	29.7	-	-	-	-	-	-	-	-	-	-	-	-	-	-
Transformer-MoS 2018.09	29.6	-	-	-	-	-	-	-	-	-	-	-	-	-	-
Transformer (Ott et al., 2018) + LayerDrop 2019.09	29.6	-	-	-	-	-	-	-	-	-	-	-	-	-	-
TaLK Convolution 2020.02	29.6	-	-	-	-	-	-	-	-	-	-	-	-	-	-
Transformer Big + Adversarial Training 2019.06	29.52	-	-	-	-	-	-	-	-	-	-	-	-	-	-
Evolved Transformer 2019.01	29.5	-	-	-	-	-	-	-	-	-	-	-	-	-	-
Transformer 2020.06	29.5	-	29	-	-	-	-	-	-	-	-	-	-	-	-
Feedback Transformer 2020.02	29.5	-	-	-	-	-	-	-	-	-	-	-	-	-	-
back-translation 2023.06	29.5	-	-	-	-	-	-	-	-	54.7	-	-	-	-	-
CNAT 2021.03	29.36	-	-	-	-	-	-	-	-	-	-	-	-	-	-
RealFormer 2020.12	29.35	-	-	-	-	-	-	-	-	-	-	-	-	-	-
Ott et al. (2018) 2019.05	29.3	-	-	-	-	-	-	-	-	-	-	-	-	-	-
Evolved Transformer 2019.01	29.3	-	-	-	-	-	-	-	-	-	-	-	-	-	-
Ott et al. 2019.01	29.3	-	28.6	-	-	-	-	-	-	-	-	-	-	-	-
Ott et al. (2018) 2018.09	29.3	-	-	-	-	-	-	-	-	-	-	-	-	-	-
Transformer (Ott et al., 2018) 2019.09	29.3	-	-	-	-	-	-	-	-	-	-	-	-	-	-
Transformer 2020.02	29.3	-	-	-	-	-	-	-	-	-	-	-	-	-	-
Ott et al. 2020.02	29.3	-	-	-	-	-	-	-	-	-	-	-	-	-	-
Transformer (Ott et al., 2018) 2020.02	29.3	-	-	-	-	-	-	-	-	-	-	-	-	-	-
Direct 2022.03	29.3	-	-	-	-	-	-	-	-	-	-	-	-	-	-
Shaw et al. (2018) 2019.05	29.2	-	-	-	-	-	-	-	-	-	-	-	-	-	-
Transformer 2019.01	29.2	-	-	-	-	-	-	-	-	-	-	-	-	-	-
Shaw et al. 2019.01	29.2	-	-	-	-	-	-	-	-	-	-	-	-	-	-
Shaw, Uszkoreit, and Vaswani (2018) 2018.09	29.2	-	-	-	-	-	-	-	-	-	-	-	-	-	-
FLOATER 2020.03	29.2	-	-	-	-	-	-	-	-	-	-	-	-	-	-
Shaw et al. 2020.02	29.2	-	-	-	-	-	-	-	-	-	-	-	-	-	-
Transformer-BIG (En-De Teacher) 2021.06	29.2	-	-	-	-	-	-	-	73	-	-	-	-	-	-
TRANSFORMER-BIG + Localness + Rel_Pos 2018.10	29.18	-	-	-	-	-	-	-	-	-	-	-	-	-	-
Transformer 2020.02	29.12	-	-	-	-	-	-	-	-	-	-	-	-	-	-
ADMIN (re-run) 2020.12	29.11	-	-	-	-	-	-	-	-	-	-	-	-	-	-
Transformer 2019.01	29.1	-	-	-	-	-	-	-	-	-	-	-	-	-	-
FLOATER 2020.03	29.1	-	-	-	-	-	-	-	-	-	-	-	-	-	-
Kitaev et al. 2020.02	29.1	-	-	-	-	-	-	-	-	-	-	-	-	-	-
baseline ours 2023.06	29.1	-	-	-	-	-	-	-	-	54.8	-	-	-	-	-
RealFormer 2020.12	29.06	-	-	-	-	-	-	-	-	-	-	-	-	-	-
ADMIN 2020.12	29.03	-	-	-	-	-	-	-	-	-	-	-	-	-	-
He et al. (2018) 2019.05	29	-	-	-	-	-	-	-	-	-	-	-	-	-	-
TRANSFORMER-BIG + D_RNN + O_CDR 2018.11	28.99	-	-	-	-	-	-	-	-	-	-	-	-	-	-
Transformer Big + (Gao et al., 2019) 2019.06	28.94	-	-	-	-	-	-	-	-	-	-	-	-	-	-
Transformer 2019.07	28.91	-	-	-	-	-	-	-	-	-	-	-	-	-	-
Ahmed et al. (2017) 2019.05	28.9	-	-	-	-	-	-	-	-	-	-	-	-	-	-
Ahmed et al. 2019.01	28.9	-	-	-	-	-	-	-	-	-	-	-	-	-	-
Dehghani et al. (2018) 2018.09	28.9	-	-	-	-	-	-	-	-	-	-	-	-	-	-
Ahmed et al. 2020.02	28.9	-	-	-	-	-	-	-	-	-	-	-	-	-	-
BiARN 2020.02	28.9	-	-	-	-	-	-	-	-	-	-	-	-	-	-
Model-level DL big 2021.05	28.9	-	-	-	-	-	-	-	-	-	-	-	-	-	-
Pretrained Transformer Large 2021.03	28.9	-	-	-	-	-	-	-	-	-	-	-	-	-	-
MASS 2022.03	28.9	-	-	-	-	-	-	-	-	-	-	-	-	-	-
TRANSFORMER-BIG + Localness 2018.10	28.89	-	-	-	-	-	-	-	-	-	-	-	-	-	-
ADMIN (re-run) 2020.12	28.85	-	-	-	-	-	-	-	-	-	-	-	-	-	-
Multi-Column Encoder 2018.04	28.84	-	-	-	-	-	-	-	-	-	-	-	-	-	-
Transformer-big 2023.05	28.81	-	-	-	-	-	-	-	-	-	53.2	-	-	-	-
baseline ours 2023.06	28.8	-	-	-	-	-	-	-	-	55.3	-	-	-	-	-
XLM 2022.03	28.8	-	-	-	-	-	-	-	-	-	-	-	-	-	-
Transformer 2019.07	28.75	-	-	-	-	-	-	-	-	-	-	-	-	-	-
Transformer 2018.09	28.7	-	-	-	-	-	-	-	-	-	-	-	-	-	-
T2R 2021.03	28.7	-	-	-	-	-	-	-	-	-	-	-	-	-	-
TRANSFORMER-BIG + O_CDR 2018.11	28.63	-	-	-	-	-	-	-	-	-	-	-	-	-	-
Transformer 2019.07	28.63	-	-	-	-	-	-	-	-	-	-	-	-	-	-
Cascaded Encoder 2018.04	28.62	-	-	-	-	-	-	-	-	-	-	-	-	-	-
FLOATER 2020.03	28.6	-	-	-	-	-	-	-	-	-	-	-	-	-	-
MathNAS 2023.11	28.6	-	-	-	-	-	-	-	-	-	-	-	-	-	-
MathNAS 2023.11	28.6	-	-	-	-	-	-	-	-	-	-	-	-	-	-
MathNAS 2023.11	28.6	-	-	-	-	-	-	-	-	-	-	-	-	-	-
mBERT 2022.03	28.6	-	-	-	-	-	-	-	-	-	-	-	-	-	-
TRANSFORMER-BIG (baseline) 2018.10	28.58	-	-	-	-	-	-	-	-	-	-	-	-	-	-
MSO 2021.05	28.58	-	-	1.36	-	-	-	-	-	-	-	-	-	-	-
ADMIN 2020.12	28.58	-	-	-	-	-	-	-	-	-	-	-	-	-	-
Global-level Selection 2021.05	28.57	-	-	-	-	1.28	-	-	-	-	-	-	-	-	-
TRANSFORMER-BASE + Localness + Rel_Pos 2018.10	28.54	-	-	-	-	-	-	-	-	-	-	-	-	-	-
Chen et al. (2018) 2019.05	28.5	-	-	-	-	-	-	-	-	-	-	-	-	-	-
Chen et al. 2019.01	28.5	-	-	-	-	-	-	-	-	-	-	-	-	-	-
Fixed-length Position Embedding 2020.03	28.5	-	-	-	-	-	-	-	-	-	-	-	-	-	-
Chen et al. 2020.02	28.5	-	-	-	-	-	-	-	-	-	-	-	-	-	-
RNMT+ 2020.02	28.5	-	-	-	-	-	-	-	-	-	-	-	-	-	-
HAT 2023.11	28.5	-	-	-	-	-	-	-	-	-	-	-	-	-	-
MathNAS 2023.11	28.5	-	-	-	-	-	-	-	-	-	-	-	-	-	-
RNMT+ 2018.04	28.49	-	-	-	-	-	-	-	-	-	-	-	-	-	-
RNMT+ 2018.04	28.49	-	-	-	-	-	-	-	-	-	-	-	-	-	-
Tay et al. (2020) 2021.05	28.47	-	-	-	-	1.17	-	-	-	-	-	-	-	-	-

Showing 100 of 379 rows