Text Classification (Classify)

In this section, we show how to use the Classify endpoint to do sentiment classification for the kind of customer satisfaction survey responses an e-commerce website may receive.

For this demo, let's assume that we want to classify a set of reviews for a newly-released feature into positive and negative classes. We might for instance have a review like this:

The item exceeded my expectations

that we want to classify as a positive review.

Naturally, the same techniques that we'll use for this problem can be used for any other task where we want to classify a given text according to a fixed set of classes.

Classify takes in example inputs with their labels, as well as the input texts we aim to classify. It then trains a classifier using the power of an embeddings model.

You can either do this with our baseline classification model (described in the next few sections), or you can train a custom classification model for better performance (described in the final section).

Labeled examples are used to demonstrate the classification task to the model. Examples provide two important pieces of information:

• The inputs and expected outputs for the task we're interested in.
• The number of output classes. Every class should appear in at least one example in the labeled examples.

In this case we will be passing in the following examples: