Overview: Natural Language Classifier in Watson Studio

Using the IBM Watson Natural Language Classifier service, you can train a model to classify text according to classes you define. IBM Watson Studio provides a collaborative environment in the cloud where you can work with your text and your Natural Language Classifier models.

 

Building a natural language classifier

You can use this graphical tool to automate building a natural language classifer. Start with a structured text file and sort it into classes that you define.

Required service
Natural Language Classifier service
Data format
Textual: CSV files with sample text and class names
Data size
Small to medium data sets
How you can build models
Provide as few as 3 text samples per class
Collaborate to classify text samples
Test the model with sample text
Add or remove test data to retrain the model
Classify text in eight languages other than English
Use Watson Natural Language Classifier APIs in applications

For more information on choosing the right tool for your data and use case, see Choosing a tool.

Natural Language Classifier service features

IBM Watson Natural Language Classifier is a service on IBM Cloud. You can use the service in your Watson Studio projects or outside of Watson Studio.

  • Classify natural language text - Train classifiers with your text examples
  • Multiple languages supported - English, Arabic, French, German, Italian, Japanese, Korean, Portuguese (Brazilian), and Spanish
  • API - Use your trained classifier in applications that you develop
    • Multi-category classification - List results for multiple classes for given text input
    • Multi-phrase classification - Classify up to 30 separate text inputs in a single API request

You can find details about supported plans and features on the Natural Language Classifier service details page external link in the IBM Cloud catalog.

 

Watson Studio tools

In Watson Studio, you can work with the Natural Language Classifier service in two ways:

  • Natural Language Classifier model builder
  • Using the API in notebooks

 

Natural Language Classifier model builder

The Natural Language Classifier model builder in Watson Studio makes it quick and easy to train and test classifiers.

See: Creating a classifier

Natural Language Classifier model builder in Watson Studio

Image of model builder

In this image, sample customer messages have been uploaded to the Natural Language Classifier model builder in Watson Studio in order to train a classifier to recognize three classes:

  • “question” : The message is asking a question
  • “problem” : The message is describing a problem or failure
  • “hi” : The message is either just social or doesn’t contain any specific technical details

 

Notebooks

Notebooks in Watson Studio provide a collaborative environment to wrangle text data for training and testing, and to use the Natural Language Classifier API.

See: Using the Natural Language Classifier API in notebooks

Using the Natural Language Classifier API in a notebook in Watson Studio

Image of a notebook

In this image, three test messages are classified by an existing, trained classifier, using the Natural Language Classifier API. Only the last part of the long output is visible in this image; but you can see the results for the third text input, which is classified as a “question”.