Deep Learning Semester Project

Project Name:

        Neural Joke Generation

Description:

        The model can generate a short joke relevant to the topic that the user specifies. It will make use of an encoder for representing user-provided topic information and an RNN decoder for joke generation.More Specifically, Gated Recurrent Units (GRUs) and LSTMs are key part for implementing the idea. I'll use Global Vectors (GloVe) to represent input and topic words.To extract the topic words from the training data, we use the part-of-speech (POS) tagger to collect the proper nouns in the jokes.

Dataset:

        http://eigentaste.berkeley.edu/dataset/

Libraries:

      1.Numpy
      
      2.Pandas
      
      3.Tensorflow
      
      4.MatplotLib