HyperAI초신경

홈 플랫폼 문서 뉴스 연구 논문 튜토리얼 데이터셋 백과사전 SOTA LLM 모델 GPU 랭킹 컨퍼런스

한국어

HyperAI초신경

Machine Translation On Iwslt2015 English 1

평가 지표

BLEU

평가 결과

이 벤치마크에서 각 모델의 성능 결과

		Paper Title	Repository
EnViT5 + MTet	40.2	MTet: Multi-domain Translation for English and Vietnamese
Tall Transformer with Style-Augmented Training	37.8	Better Translation for Vietnamese	-
Transformer+BPE-dropout	33.27	BPE-Dropout: Simple and Effective Subword Regularization
Transformer+BPE+FixNorm+ScaleNorm	32.8	Transformers without Tears: Improving the Normalization of Self-Attention
Transformer+LayerNorm-simple	31.4	Understanding and Improving Layer Normalization
CVT	29.6	Semi-Supervised Sequence Modeling with Cross-View Training
Self-Adaptive Control of Temperature	29.12	Learning When to Concentrate or Divert Attention: Self-Adaptive Attention Temperature for Neural Machine Translation
SAWR	29.09	Syntax-Enhanced Neural Machine Translation with Syntax-Aware Word Representations	-
DeconvDec	28.47	Deconvolution-Based Global Decoding for Neural Machine Translation
LSTM+Attention+Ensemble	26.4	Stanford Neural Machine Translation Systems for Spoken Language Domains	-
NLLB-200	-	No Language Left Behind: Scaling Human-Centered Machine Translation

0 of 11 row(s) selected.