Skip to main content


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

Improve the management of text extraction models through entity types (8.3)

Updated on May 3, 2021

Create a case, populate a form, or route an assignment by using entity types that locate and classify keywords and phrases in unstructured text into such classes as Person Name, Monetary Value, Currency, Location, Organization, and so on. Each entity type can integrate such detection methods as Apache Ruta, keywords, and machine learning in order of priority to provide versatile and robust text extraction.

Entity types simplify the management of complex models that contain entities that are nested. For example, the Address entity type can nest such entity types as Country, Province, City, Postal Code, Street, and so on. 

The following example demonstrates the currency entity that is an entity type that can be detected through a list of associated keywords and pattern matching:

Configuring a keyword-based entity type in Prediction Studio

See the following video to learn how to create nested entity types:

Creating nested entity types in Prediction Studio

In addition, the number of default text extraction models has increased. You can now reuse these default models to implement text analytics in your application faster, without the need to gather the training data or to go through the entire process of building models. View and test new entity types, for example, us_airport, time_unit, organization_suffix, area_unit, and so on, by accessing the System Entities and Unit Entities text extraction models in Prediction Studio.

For more information, see:

  • Previous topic Evaluate event strategies through unit testing (8.3)
  • Next topic Improve your custom predictive models through machine learning as a service (8.3)

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