Like other machine-learned models, our intent classifier works at its best if the different class triggers have roughly the same amount of learning examples. The 'Improve the balance' panel allows not only to easily identify existing imbalances with regard to the number of learning examples for each trigger, but also provides suggestions for learning examples to be added. This makes it easy and convenient for you to get a more balanced and thus more reliable intent model.
In order to get a balanced model, we simply have to make sure that all class triggers have roughly the same amount of learning examples. However, there is no need for all class triggers to have the exact same amount of training data. We recommend roughly 15 learning examples for each class trigger when you first build your solution. As soon as you have access to real user inputs, you may then add more learning examples to your class triggers . The following video illustrates how to go about this. Please make sure to adjust your loudspeakers before playing the video.
Was this page helpful?