Machine Translation On Wmt2014 English French

評価指標

BLEU score

評価結果

このベンチマークにおける各モデルのパフォーマンス結果

モデル名	BLEU score	Paper Title	Repository
CSLM + RNN + WP	34.54	Learning Phrase Representations using RNN Encoder-Decoder for Statistical Machine Translation
LightConv	43.1	Pay Less Attention with Lightweight and Dynamic Convolutions
GRU+Attention	26.4	Can Active Memory Replace Attention?
Transformer Big	41.0	Attention Is All You Need
RNMT+	41.0	The Best of Both Worlds: Combining Recent Advances in Neural Machine Translation
Deep-Att	35.9	Deep Recurrent Models with Fast-Forward Connections for Neural Machine Translation
Transformer Base	38.1	Attention Is All You Need
MoE	40.56	Outrageously Large Neural Networks: The Sparsely-Gated Mixture-of-Experts Layer
LSTM	34.8	Sequence to Sequence Learning with Neural Networks
RNN-search50*	36.2	Neural Machine Translation by Jointly Learning to Align and Translate
Transformer+BT (ADMIN init)	46.4	Very Deep Transformers for Neural Machine Translation
ResMLP-12	40.6	ResMLP: Feedforward networks for image classification with data-efficient training
Noisy back-translation	45.6	Understanding Back-Translation at Scale
Rfa-Gate-arccos	39.2	Random Feature Attention	-
Unsupervised PBSMT	28.11	Phrase-Based & Neural Unsupervised Machine Translation
TransformerBase + AutoDropout	40	AutoDropout: Learning Dropout Patterns to Regularize Deep Networks
ConvS2S (ensemble)	41.3	Convolutional Sequence to Sequence Learning
PBMT	37	-	-
Transformer (big) + Relative Position Representations	41.5	Self-Attention with Relative Position Representations
Unsupervised attentional encoder-decoder + BPE	14.36	Unsupervised Neural Machine Translation

0 of 57 row(s) selected.