Get our free extension to see links to code for papers anywhere online!

Chrome logo  Add to Chrome

Firefox logo Add to Firefox

Single Headed Attention RNN: Stop Thinking With Your Head



Stephen Merity

* Addition of citations and contextual results (no attention head, single attention head, attention per layer), removal of wordpiece WikiText-103 numbers due to normalization issues, fix of SHA attention figure Q arrow, other minor fixes 

   Access Paper or Ask Questions

An Analysis of Neural Language Modeling at Multiple Scales



Stephen Merity , Nitish Shirish Keskar , Richard Socher


   Access Paper or Ask Questions

A Flexible Approach to Automated RNN Architecture Generation



Martin Schrimpf , Stephen Merity , James Bradbury , Richard Socher


   Access Paper or Ask Questions

Regularizing and Optimizing LSTM Language Models



Stephen Merity , Nitish Shirish Keskar , Richard Socher


   Access Paper or Ask Questions

Revisiting Activation Regularization for Language RNNs



Stephen Merity , Bryan McCann , Richard Socher


   Access Paper or Ask Questions

Quasi-Recurrent Neural Networks



James Bradbury , Stephen Merity , Caiming Xiong , Richard Socher

* Submitted to conference track at ICLR 2017 

   Access Paper or Ask Questions

Pointer Sentinel Mixture Models



Stephen Merity , Caiming Xiong , James Bradbury , Richard Socher


   Access Paper or Ask Questions

Dynamic Memory Networks for Visual and Textual Question Answering



Caiming Xiong , Stephen Merity , Richard Socher


   Access Paper or Ask Questions