Creating a Natural Language Classifier model

You can train IBM Watson Natural Language Classifier models with your own training text to meet your specific text-analysis goals. This topic describes how to use the Natural Language Classifier model builder in IBM Watson Studio to create a classifier.

 

Demonstration

Watch this video to see how to create and train a Natural Language Classifier model using customer support ticket text examples to classify loan types.

Procedure

  1. Prepare your text training data
    Collect a minimum of three example text passages for each of a minimum of two classes in a .csv file, and then upload the file to your project.
     
  2. Train your model
    In the Natural Language Classifier model builder, define your classes and add text examples.
     
  3. Test your trained model
    After your model is trained, you can use the Test area of the model builder to classify test text passages using your model.
     
  4. (Optional) Retrain your model
    You can improve the performance of your model by adding or removing training data and then retraining the model.
     

 

Next steps