Importing types from the Textual library
Last updated
Was this helpful?
Textual provides access to a library of entity types that we created from trained models.
These entity types cover a range of additional types of values. You might be able to use these types instead of adding custom types.
You can search for and select types to import that apply to your datasets. The imported types display in the list of custom entity types.
To start an import, on the Entity Types page, either:
Click Import type, then select Pre-trained library.
Click Add Entity Type. On the Add entity type panel, click Pre-trained model-based entity types, then click Next.
Textual displays the Pre-trained Type Library page.

For each type, the list includes:
The name of the type.
Tags to help categorize the type. For example, a tag might identify a type as being related to government or healthcare.
Whether the type was imported.
To search for a type based on its name, in the search field, begin to type the name or description text.
To filter the list based on the assigned tags:
Click Filter.
In the tags list, check the tags to include.
When you click the type, the details panel displays.

The details panel includes:
The type name.
Example values.
Assigned tags.
A longer description of the type.
The details panel provides an option to test the type against an input string that you provide. This can help determine if the pre-trained type would detect known values in your files.
When you first display details panel, it includes an example text string that contains a detected value.
To test your own value, in the Input text area, type a text string that contains the value to test.
The Output text area highlights the type values that were detected in the input string.
From the type details panel, to import a type, click Import.
Textual adds the imported type to the list on the Entity Types page.
For a type that is already imported, the Import button is replaced with a Remove button. To remove the imported type, click Remove.
Last updated
Was this helpful?
Was this helpful?