R-Transformer: Recurrent Neural Network Enhanced Transformer

Benchmark Model Rank Results
language-modelling-on-penn-treebank-characterR-Transformer#14Bit per Character (BPC): 1.24
language-modelling-on-penn-treebank-wordR-Transformer#39Test perplexity: 84.38
sequential-image-classification-on-sequentialR-Transformer#30Unpermuted Accuracy: 99.1%