While state-of-the-art NLP models have demonstrated excellent performanc...
In this paper we present a controlled study on the linearized IRM framew...
While sequence-to-sequence (seq2seq) models achieve state-of-the-art
per...
Seq2seq models based on Recurrent Neural Networks (RNNs) have recently
r...
We introduce LL-RNNs (Log-Linear RNNs), an extension of Recurrent Neural...