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