Pervasive Attention

Reported on 2 benchmarks across 1 task · 1 paper · 1 SOTA

Note: results are matched by exact model name. Different papers may use the same name for different model variants.

Natural Language Processing2 results

Machine TranslationonIWSLT2015 German-English
BLEU score· 2018-08-11
34.18
best: 36.2 (PS-KD)
SOTA
Pervasive Attention: 2D Convolutional Neural Networks for Sequence-to-Sequence Prediction arXiv:1808.03867
Machine TranslationonIWSLT2015 English-German
BLEU score· 2018-08-11
27.99
best: 30 (PS-KD)
Pervasive Attention: 2D Convolutional Neural Networks for Sequence-to-Sequence Prediction arXiv:1808.03867