Overview of the IBM Watson Natural Language Classifier service

The IBM Watson™ Natural Language Classifier service uses machine learning algorithms to return the top matching predefined classes for short text inputs.

How you use the service

The following image shows the process of creating and using the classifier:

Classification process

What to use the service for

The Natural Language Classifier service can help your application understand the language of short texts and make predictions about how to handle them. A classifier learns from your example data and then can return information for texts that it is not trained on.

One use of the service is for customer support. For example, you can use the service to take predictive actions, such as routing users' questions to the correct person or classifying issues by severity. And by incorporating the Speech to Text service in your app, you can also route voice questions to a specific department.

Supported languages

The Natural Language Classifier service supports English, Arabic, French, German, Japanese, Italian, Portuguese, and Spanish.

Next steps

Questions and feedback

Find answers to your questions about the Natural Language Classifier service in our developer communities:

  • For programming questions, go to the Watson forums on Stack Overflow.
  • For Watson products and services, go to the Watson forum on dW Answers.
  • To read posts about Watson services, go to the Watson blog.