Machine Translation On Iwslt2014 German

Métriques

BLEU score

Résultats

Résultats de performance de divers modèles sur ce benchmark

Nom du modèle	BLEU score	Paper Title	Repository
Transformer	34.44	Attention Is All You Need
Rfa-Gate-arccos	34.4	Random Feature Attention	-
TaLK Convolutions	35.5	Time-aware Large Kernel Convolutions
Bi-SimCut	38.37	Bi-SimCut: A Simple Strategy for Boosting Neural Machine Translation
Mask Attention Network (small)	36.3	Mask Attention Networks: Rethinking and Strengthen Transformer
Cutoff+Knee	37.78	Wide-minima Density Hypothesis and the Explore-Exploit Learning Rate Schedule
CNAT	31.15	Non-Autoregressive Translation by Learning Target Categorical Codes
Minimum Risk Training [Edunov2017]	32.84	Classical Structured Prediction Losses for Sequence to Sequence Learning
BiBERT	38.61	BERT, mBERT, or BiBERT? A Study on Contextualized Embeddings for Neural Machine Translation
LightConv	34.8	Pay Less Attention with Lightweight and Dynamic Convolutions
TransformerBase + AutoDropout	35.8	AutoDropout: Learning Dropout Patterns to Regularize Deep Networks
DynamicConv	35.2	Pay Less Attention with Lightweight and Dynamic Convolutions
Transformer + R-Drop	37.25	R-Drop: Regularized Dropout for Neural Networks
Transformer	35.1385	Guidelines for the Regularization of Gammas in Batch Normalization for Deep Residual Networks	-
Back-Translation Finetuning	28.83	Tag-less Back-Translation	-
Local Joint Self-attention	35.7	Joint Source-Target Self Attention with Locality Constraints
Transformer + R-Drop + Cutoff	37.90	R-Drop: Regularized Dropout for Neural Networks
Data Diversification	37.2	Data Diversification: A Simple Strategy For Neural Machine Translation
UniDrop	36.88	UniDrop: A Simple yet Effective Technique to Improve Transformer without Extra Cost	-
Actor-Critic [Bahdanau2017]	28.53	An Actor-Critic Algorithm for Sequence Prediction

0 of 34 row(s) selected.