HyperAI超神経
ホームニュース最新論文チュートリアルデータセット百科事典SOTALLMモデルGPU ランキング学会
検索
サイトについて
HyperAI超神経

Machine Translation On Wmt2014 English German

評価指標

BLEU score
Hardware Burden
Operations per network pass

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
Hardware Burden
Operations per network pass
Paper TitleRepository
Transformer Big + adversarial MLE29.52Improving Neural Language Modeling via Adversarial Training
MAT---Multi-branch Attentive Transformer
AdvAug (aut+adv)29.57--AdvAug: Robust Adversarial Augmentation for Neural Machine Translation-
CMLM+LAT+4 iterations27.35Incorporating a Local Translation Mechanism into Non-autoregressive Translation-
FlowSeq-large (IWD n = 15)22.94FlowSeq: Non-Autoregressive Conditional Sequence Generation with Generative Flow
Transformer (ADMIN init)30.1--Very Deep Transformers for Neural Machine Translation
MUSE(Parallel Multi-scale Attention)29.9MUSE: Parallel Multi-Scale Attention for Sequence to Sequence Learning
Transformer-DRILL Base28.1Deep Residual Output Layers for Neural Language Generation
Transformer Big with FRAGE29.11FRAGE: Frequency-Agnostic Word Representation
GLAT25.21--Glancing Transformer for Non-Autoregressive Neural Machine Translation
PartialFormer29.56--PartialFormer: Modeling Part Instead of Whole for Machine Translation
Bi-SimCut30.78--Bi-SimCut: A Simple Strategy for Boosting Neural Machine Translation
Transformer + SRU28.434GSimple Recurrent Units for Highly Parallelizable Recurrence
PBMT20.7--
Local Joint Self-attention29.7Joint Source-Target Self Attention with Locality Constraints
Lite Transformer26.5--Lite Transformer with Long-Short Range Attention
Average Attention Network (w/o FFN)26.05--Accelerating Neural Transformer via an Average Attention Network
Unsupervised NMT + Transformer17.16Phrase-Based & Neural Unsupervised Machine Translation
KERMIT28.7KERMIT: Generative Insertion-Based Modeling for Sequences-
T2R + Pretrain28.7Finetuning Pretrained Transformers into RNNs
0 of 91 row(s) selected.