Now that we have learned the core concepts of computational linguistics, and trained relations from the provided dataset, we can use this learning to implement a language model that can perform a task.
In this section, we will build a text classification model to perform sentiment analysis. For classification, we will be using a combination of CNN and a pre-trained word2vec model, which we learned about in the previous section of this chapter.
This task is the simulation of our hypothetical business use case of taking text responses from restaurant patrons and classifying what they text back into meaningful classes for the restaurant.
We have been inspired by Denny Britz's (https://twitter.com/dennybritz) work on Implementing a CNN for Text Classification in TensorFlow (http://www.wildml.com/2015/12/implementing-a-cnn-for...
