HyperAIHyperAI超神经

Command Palette

Search for a command to run...

算力平台

Machine Translation On Wmt2016 English German

评估指标

BLEU score

评测结果

各个模型在此基准测试上的表现结果

Paper Title
MADL40.68Multi-Agent Dual Learning
Attentional encoder-decoder + BPE34.2Edinburgh Neural Machine Translation Systems for WMT 16
Linguistic Input Features28.4Linguistic Input Features Improve Neural Machine Translation
DeLighT28.0DeLighT: Deep and Light-weight Transformer
FLAN 137B (zero-shot)27.0Finetuned Language Models Are Zero-Shot Learners
Transformer26.7On the adequacy of untuned warmup for adaptive optimization
FLAN 137B (few-shot, k=11)26.1Finetuned Language Models Are Zero-Shot Learners
BiRNN + GCN (Syn + Sem)24.9Exploiting Semantics in Neural Machine Translation with Graph Convolutional Networks
SMT + iterative backtranslation (unsupervised) 18.23Unsupervised Statistical Machine Translation
Unsupervised NMT + weight-sharing10.86Unsupervised Neural Machine Translation with Weight Sharing
Unsupervised S2S with attention9.64Unsupervised Machine Translation Using Monolingual Corpora Only
Exploiting Mono at Scale (single)-Exploiting Monolingual Data at Scale for Neural Machine Translation
0 of 12 row(s) selected.
Machine Translation On Wmt2016 English German | SOTA | HyperAI超神经