Skip to main content

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

Testing an email parser

Updated on July 5, 2022

Test an email parser model to ensure that it extracts the email parts, such as the signature, body, and disclaimer, correctly. Testing is a good practice after you add training data to an email parser.

  1. Open the text prediction:
    1. In the navigation pane of App Studio, click Channels.
    2. In the Current channel interfaces section, click the icon that represents a channel for which you want to configure the text prediction.
    3. On the channel configuration page, click the Behavior tab, and then click Open text prediction.
  2. Click the Settings tab.
  3. In the Preprocessing model section, copy the name of the parser model.
  4. In the navigation pane of Prediction Studio, click Models.
  5. Search for the email parser model, and then open it.
  6. In the upper-left corner of the email parser model, click Test.
    Test option in the email parser configuration
    The email parser model is open in Prediction Studio. The Test button is available in the upper-left corner.
  7. In the Test window, enter a sample message, and then click Test.
  8. Review the results, and then verify whether the model parses the text correctly.
    Results of testing the email parser with sample text
    A short email is used as sample test. Test results show that the model recognized the email body and signature.
What to do next: Unsatisfactory results, such as when the email parser does not properly detect the email body, signature, or disclaimer, usually indicate that the model requires more training data. For more information, see Training an email parser.

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

Close Deprecation Notice
Contact us