List your company
ResearchFormerly WizWand

Machine Translation on WMT En-Tr 17

25.8BLEUmRASP2
8.84813.24917.6522.051Oct 7, 2020Jan 2, 2021Mar 31, 2021Jun 27, 2021Sep 22, 2021Dec 19, 2021Mar 17, 2022
Updated 8mo ago

Evaluation results

MethodLinks
mRASP2Training Strategy=unified multilingual, Model Architecture (Layers)=12 layers2021.0525.8
mRASPTraining Strategy=unified multilingual, Model Architecture (Layers)=12 layers, Fine-tuning Status=without fine-tune2021.0525.2
CeMATPre-training=CeMAT, Fine-tuning=true, Beam Size=52022.0323.9
CeMATPre-training=CeMAT, Fine-tuning=true, Beam Size=52022.0323.6
mRASPTraining Strategy=pre-train & fine-tuned, Fine-tuning Status=fine-tuned2021.0523.4
mRASPPre-training=mRASP, Fine-tuning=true, Beam Size=52022.0323.4
m-TransformerTraining Strategy=unified multilingual, Model Architecture (Layers)=12 layers2021.0523.1
mBARTTraining Strategy=pre-train & fine-tuned, Fine-tuning Status=fine-tuned2021.0522.5
mBARTPre-training=mBART, Fine-tuning=true, Beam Size=52022.0322.5
mRASP2020.1020
mRASPPre-training=mRASP, Fine-tuning=true, Beam Size=52022.0320
mBART2020.1017.8
mBARTPre-training=mBART, Fine-tuning=true, Beam Size=52022.0317.8
Transformer-12Training Strategy=bilingual, Model Architecture (Layers)=12 layers2021.0512.2
DirectTraining=From scratch, Beam Size=52022.0312.2
Direct2020.109.5
DirectTraining=From scratch, Beam Size=52022.039.5