WordCloud is a visualization of the frequency of words in a given text. Certain words appear bigger than the other when their frequency of occurrence is higher. WordClouds may not be an appropriate visualization method in context to the importance of words in a given text.

There are many NLP tasks like text summarization, question-answering, sentence prediction to name a few. One method to get these tasks done is using a pre-trained model. Instead of training a model from scratch for NLP tasks using millions of annotated texts each time, a general language representation is created by training a model on a huge amount of data. This is called a pre-trained model. This pre-trained model is then fine-tuned for each NLP tasks according to need.

So let’s break it down. What are generative models? Broadly speaking we have two kinds of models, Generative and Discriminative. The models that we built for classification tasks are discriminative like SVM, logistic regression.