Skip to main content


         This documentation site is for previous versions. Visit our new documentation site for current releases.      
 

General troubleshooting tips for NLP

Updated on July 5, 2022

When you encounter a problem while working with the natural language processing (NLP) features of your application, take these steps to identify and understand the underlying cause.

  1. Check whether your text is working as expected in the underlying text prediction by testing the prediction.
  2. Based on the test results, perform one of the following actions:
  3. If you are still unsure about the cause of the issue, test the model independently, using the same text.
    Note: Text predictions can filter out some output based on general text prediction settings, which you might notice when you test the text directly on the model and not in the text prediction.
  4. If the model detects topics or entities correctly, but you did not get the same results when you tested the text prediction, check the general settings of the text prediction.
    Note: Text prediction settings can filter out some of the output that you expect to see.

Have a question? Get answers now.

Visit the Support Center to ask questions, engage in discussions, share ideas, and help others.

Did you find this content helpful?

Want to help us improve this content?

We'd prefer it if you saw us at our best.

Pega.com is not optimized for Internet Explorer. For the optimal experience, please use:

Close Deprecation Notice
Contact us