Language Modeling with Gated Convolutional Networks
Open paper
Benchmark
Model
Rank
Results
language-modelling-on-one-billion-word
GCNN-14 bottleneck
#19
PPL: 31.9
language-modelling-on-wikitext-103
GCNN-8
#71
Test perplexity: 37.2
language-modelling-on-wikitext-103
GCNN-8
#75
Test perplexity: 44.9
Rank counts only results with a code link.