OpenCodePapers

machine-translation-on-wmt2014-english-french

Machine Translation
Dataset Link
Results over time
Click legend items to toggle metrics. Hover points for model names.
Leaderboard
Click a sortable column header to sort.
PaperCodeBLEU scoreSacreBLEUHardware BurdenOperations per network passModelNameReleaseDate
Very Deep Transformers for Neural Machine Translation✓ Link46.444.4Transformer+BT (ADMIN init)2020-08-18
Understanding Back-Translation at Scale✓ Link45.643.8180GNoisy back-translation2018-08-28
Pre-training Multilingual Neural Machine Translation by Leveraging Alignment Information✓ Link44.341.7mRASP+Fine-Tune2020-10-07
R-Drop: Regularized Dropout for Neural Networks✓ Link43.95Transformer + R-Drop2021-06-28
Very Deep Transformers for Neural Machine Translation✓ Link43.841.8Transformer (ADMIN init)2020-08-18
Understanding the Difficulty of Training Transformers✓ Link43.8Admin2020-04-17
Incorporating BERT into Neural Machine Translation✓ Link43.78BERT-fused NMT2020-02-17
MUSE: Parallel Multi-Scale Attention for Sequence to Sequence Learning✓ Link43.5MUSE(Paralllel Multi-scale Attention)2019-11-17
Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer✓ Link43.4T52019-10-23
Joint Source-Target Self Attention with Locality Constraints✓ Link43.3Local Joint Self-attention2019-05-16
Depth Growing for Neural Machine Translation✓ Link43.2724GDepth Growing2019-07-03
Scaling Neural Machine Translation✓ Link43.255GTransformer Big2018-06-01
Pay Less Attention with Lightweight and Dynamic Convolutions✓ Link43.2DynamicConv2019-01-29
Time-aware Large Kernel Convolutions✓ Link43.2TaLK Convolutions2020-02-08
Pay Less Attention with Lightweight and Dynamic Convolutions✓ Link43.1LightConv2019-01-29
Learning to Encode Position for Transformer with Continuous Dynamical Model✓ Link42.7FLOATER-large2020-03-13
OmniNet: Omnidirectional Representations from Transformers✓ Link42.6OmniNetP2021-03-01
Fast and Simple Mixture of Softmaxes with BPE and Hybrid-LightRNN for Language Generation✓ Link42.1Transformer Big + MoS2018-09-25
Finetuning Pretrained Transformers into RNNs✓ Link42.1T2R + Pretrain2021-03-24
Synthesizer: Rethinking Self-Attention in Transformer Models✓ Link41.85Synthesizer (Random + Vanilla)2020-05-02
HAT: Hardware-Aware Transformers for Efficient Natural Language Processing✓ Link41.8Hardware Aware Transformer2020-05-28
Self-Attention with Relative Position Representations✓ Link41.5Transformer (big) + Relative Position Representations2018-03-06
Deliberation Networks: Sequence Generation Beyond One-Pass Decoding41.5Stack 4-layer RNNSearch + Dual Learning + Deliberation Network2017-12-01
Weighted Transformer Network for Machine Translation✓ Link41.4Weighted Transformer (large)2017-11-06
Convolutional Sequence to Sequence Learning✓ Link41.3ConvS2S (ensemble)2017-05-08
The Evolved Transformer✓ Link41.3Evolved Transformer Big2019-01-30
The Best of Both Worlds: Combining Recent Advances in Neural Machine Translation✓ Link41.0132G2.81GRNMT+2018-04-26
Attention Is All You Need✓ Link41.023G2300000000.0GTransformer Big2017-06-12
The Evolved Transformer✓ Link40.6Evolved Transformer Base2019-01-30
ResMLP: Feedforward networks for image classification with data-efficient training✓ Link40.6ResMLP-122021-05-07
Outrageously Large Neural Networks: The Sparsely-Gated Mixture-of-Experts Layer✓ Link40.56142GMoE2017-01-23
Memory-Efficient Adaptive Optimization✓ Link40.5Transformer2019-01-30
Convolutional Sequence to Sequence Learning✓ Link40.46143GConvS2S2017-05-08
ResMLP: Feedforward networks for image classification with data-efficient training✓ Link40.3ResMLP-62021-05-07
AutoDropout: Learning Dropout Patterns to Regularize Deep Networks✓ Link40TransformerBase + AutoDropout2021-01-05
Google's Neural Machine Translation System: Bridging the Gap between Human and Machine Translation✓ Link39.9279GGNMT+RL2016-09-26
Lite Transformer with Long-Short Range Attention✓ Link39.6Lite Transformer2020-04-24
Deep Recurrent Models with Fast-Forward Connections for Neural Machine Translation✓ Link39.2119GDeep-Att + PosUnk2016-06-14
Random Feature Attention39.2Rfa-Gate-arccos2021-03-03
Attention Is All You Need✓ Link38.123G330000000.0GTransformer Base2017-06-12
Addressing the Rare Word Problem in Neural Machine Translation✓ Link37.5LSTM6 + PosUnk2014-10-30
[]()37PBMT
Sequence to Sequence Learning with Neural Networks✓ Link36.5SMT+LSTM52014-09-10
Neural Machine Translation by Jointly Learning to Align and Translate✓ Link36.2RNN-search50*2014-09-01
Deep Recurrent Models with Fast-Forward Connections for Neural Machine Translation✓ Link35.9Deep-Att2016-06-14
A Convolutional Encoder Model for Neural Machine Translation✓ Link35.7Deep Convolutional Encoder; single-layer decoder2016-11-07
Sequence to Sequence Learning with Neural Networks✓ Link34.8LSTM2014-09-10
Learning Phrase Representations using RNN Encoder-Decoder for Statistical Machine Translation✓ Link34.54CSLM + RNN + WP2014-06-03
Finetuned Language Models Are Zero-Shot Learners✓ Link33.9FLAN 137B (zero-shot)2021-09-03
Finetuned Language Models Are Zero-Shot Learners✓ Link33.8FLAN 137B (few-shot, k=9)2021-09-03
Recurrent Neural Network Regularization✓ Link29.03Regularized LSTM2014-09-08
Phrase-Based & Neural Unsupervised Machine Translation✓ Link28.11Unsupervised PBSMT2018-04-20
Phrase-Based & Neural Unsupervised Machine Translation✓ Link27.6PBSMT + NMT2018-04-20
Can Active Memory Replace Attention?✓ Link26.4GRU+Attention2016-10-27
Unsupervised Statistical Machine Translation✓ Link26.22SMT + iterative backtranslation (unsupervised)2018-09-04
Phrase-Based & Neural Unsupervised Machine Translation✓ Link25.14Unsupervised NMT + Transformer2018-04-20
Unsupervised Neural Machine Translation✓ Link14.36Unsupervised attentional encoder-decoder + BPE2017-10-30
Check out how to contribute new results.