gistfile1.txt

Text generation models typically learn the distribution of a text and
  used this learned information to generate text themselves. By tuning
  various hyperparameters, it is possible to finetune the tradeoff between
  the deviation of the text from the distribution and the robustness of
  the text.
  
  I present a way to extend this ability of generative models to learn
  multiple distributions in order to generate a style of text
  that is unique from both distributions.
  I also discuss ways to regularize the presented model using Generative
  Adversarial Networks(GANs) and governing the contribution of each particular
  style of text.
  
  Evaluating models that generate unique texts are hard to evaluate.I
  also present a way to evaluate the generated texts from the model.

  Recurrent Neural Networks(RNNs) have shown to have superior performance
  when dealing with sequences that have long term dependencies.
  I employ RNNs as the text generation model and adversarial networks as
  the regularization mechanism.