Tweeted By @evolvingstuff
Maybe attention isn't *all* we need...
— Thomas Lahore (@evolvingstuff) July 15, 2019
R-Transformer: Recurrent Neural Network Enhanced Transformer
"empirical results show that R-Transformer outperforms the state-of-the-art methods by a large margin in most of the tasks"https://t.co/DoExWtUttMhttps://t.co/hvWwMbWK0G pic.twitter.com/v9NfzEtztK