Jonathan Donnelly

Extracting representations from the LM

2

Hello, Is it possible to extract features from the language model using the current version of the code? For example, given a string such as "the cow goes moo", can...

Tips for training on GPU?

2

Hello, I am trying to train this model in Tensorflow using the values for batch size and sequence length given in the paper (batches of 128 and sequence length of...

Weight Initialization

4

Hello, Thank you very much for sharing this code. I am attempting to re-train a model like this from scratch and was wondering which weight initialization method was used for...