Retraining a Natural Language Classifier model

There are many reasons why you might want to retrain your IBM Watson Natural Language Classifier model, such as: testing of a new model indicates performance is not as good as you need; or current input data for an older model has drifted away from the data used to train the model. In IBM Watson Studio, you can "retrain" a model by using the Natural Language Classifier model builder, which has the effect of deleting the original model and creating a new model with a new model ID.

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

Figure 1. Video iconNatural Language Classifier Model
This video shows you how to edit and retrain a Natural Language Classifier model using customer support ticket text examples to classify loan types.

Before you begin

Train your model

 

Procedure

  1. From the Assets page of your project, open the Natural Language Classifier model builder by clicking on your trained classifier.
     
  2. Click Edit and Retrain.
     
  3. Edit your model: remove training text examples from your model, add more training text examples to your model, or change the class with which a training text example is associated.
     
  4. Click Train Model.
     
  5. Wait for the retraining process to finish. You can leave the Natural Language Classifier model builder while the process runs. You can monitor the status of the training process by looking at the status of the model on the Assets page of your project.

 

Updating your apps

When you retrain a Natural Language Classifier model by using the Natural Language Classifier model builder in Watson Studio, the original model is deleted and a new model is created with a new model ID. This means that you must update the model ID in any apps that use the model to classify text.