What is IBM Watson® Natural Language Classifier?


Ultra-simple training

Upload a .csv file with your training data and labels and you’re ready to go in 15 minutes or less — it’s that easy.

High accuracy on small datasets

Under the covers, Natural Language Classifier combines SVMs and a Convolutional Neural Network to provide you with the highest accuracy possible.

Customizable applications

Use Python, Ruby, Go, Java, Node or Curl to manage the API and integrate it into your applications.


Categorize text data

Automate workflows, extract insights and improve search and discovery with text you can easily categorize.

Evaluate results

Update training data based on classification results to improve your confidence scores.

Train via Tooling or an API

Access capabilities through the API or non-technical tooling in order to build, train and manage classifiers, regardless of your technical skills.


Tutorial walk-through

An easy, step-by-step guide to getting started, and support for the build and maintenance of your application

Sample applications

Tutorials and demos with code that you can leverage to jumpstart your development

API reference

A step-by-step technical guide to building an assistant in multiple programming languages


A collection of REST APIs and SDKs that uses AI to solve complex problems. Includes Python, Node, Java and more


Get the latest Watson announcements, tutorials and feature details

IBM Code

More than 100 open source programs, a library of knowledge resources, Developer Advocates ready to help and a global community of developers

Get started in minutes with Natural Language Classifier at no cost