Attribute extrapolation in sample generation is challenging for deep neu...
Interpretability techniques in NLP have mainly focused on understanding
...
Class-conditional language models (CC-LMs) can be used to generate natur...
We propose Taylorized training as an initiative towards better
understan...
This research note combines two methods that have recently improved the ...
Conversational agents are gaining popularity with the increasing ubiquit...
We present Edina, the University of Edinburgh's social bot for the Amazo...
We present methodology for using dynamic evaluation to improve neural
se...
We introduce multiplicative LSTM (mLSTM), a recurrent neural network
arc...
Recurrent Neural Networks (RNNs) have long been recognized for their
pot...