HyperAIHyperAI
HomeNewsLatest PapersTutorialsDatasetsWikiSOTALLM ModelsGPU LeaderboardEvents
Search
About
HyperAIHyperAI

Machine Translation On Iwslt2015 German

Metrics

BLEU score

Results

Performance results of various models on this benchmark

Model Name
BLEU score
Paper TitleRepository
Word-level CNN w/attn, input feeding24.0Sequence-to-Sequence Learning as Beam-Search Optimization
Conv-LSTM (deep+pos)30.4A Convolutional Encoder Model for Neural Machine Translation
QRNN19.41Quasi-Recurrent Neural Networks
FlowSeq-base24.75FlowSeq: Non-Autoregressive Conditional Sequence Generation with Generative Flow
Denoising autoencoders (non-autoregressive)32.43Deterministic Non-Autoregressive Neural Sequence Modeling by Iterative Refinement
Word-level LSTM w/attn20.2Sequence Level Training with Recurrent Neural Networks
ConvS2S32.31Convolutional Sequence to Sequence Learning
Transformer with FRAGE33.97FRAGE: Frequency-Agnostic Word Representation
ConvS2S+Risk32.93Classical Structured Prediction Losses for Sequence to Sequence Learning
RNNsearch29.98An Actor-Critic Algorithm for Sequence Prediction
Bi-GRU (MLE+SLE)28.53Neural Machine Translation by Jointly Learning to Align and Translate
Pervasive Attention34.18Pervasive Attention: 2D Convolutional Neural Networks for Sequence-to-Sequence Prediction
NPMT + language model30.08Towards Neural Phrase-based Machine Translation
PS-KD36.20Self-Knowledge Distillation with Progressive Refinement of Targets
DCCL29.56Compressing Word Embeddings via Deep Compositional Code Learning
0 of 15 row(s) selected.
Machine Translation On Iwslt2015 German | SOTA | HyperAI