Advanced Online Learning Options window
This window is used to customize the way online learning is deployed.
- General Settings
-
This group has the following settings:
- Group by field
-
Select from the list the field value you want to use to tag the group to facilitate sorts and filtering. For example, you may use the name of a supplier as the group value. The value of this field is saved in an additional data field. (Default: Classification Result)
- Use Classification Online Learning
-
Select this setting if you want to use online learning to improve your classification results over time.
This is a project-wide setting that affects all classes in your project. (Default: Selected)
- Use Extraction Online Learning
-
Select this setting if you want to use this type of online learning. This is a project-wide setting that affects any class with one or more trainable locator. (Default: Selected)
If this setting is selected, the Use for Extraction Online Learning button is displayed in the Validation toolbar.
- Allow Problem Reporting
-
Select this setting if you want to allow documents to be marked as a problem during production. This is a project-wide setting that affects any class with one or more trainable locator, and requires an administrator to periodically retrain the project. (Default: Selected)
If this setting is selected, the Report a Problem button is displayed in the Validation toolbar.
- Classification Online Learning Settings
-
This group has the following settings:
- Maximum documents stored for import
-
Enter a number between 100 and 20,000 to limit the number of documents to store for import. (Default: 2000)
- Use dynamic classifiers during classification
-
This setting is used to create dynamic classifiers for your project. (Default: Selected)
If selected, all of the documents marked for Classification Online Learning are used by the dynamic classifiers when a document is classified. This means that any documents collected since the last time you trained your project do not have to wait until you train again to be useful.
Dynamic classifiers cannot be used in combination with document separation.
- Number of documents required to repeat the training of the content classifiers
-
Enter a value between 1 and 10,000 to specify how many new documents must be collected before another iteration of training is performed and the content classifiers are updated. (Default: 1)
- Extraction Online Learning Settings
-
This group has the following settings:
- Maximum documents stored for import
-
Enter a number between 100 and 20,000 to limit the number of documents to store for import. (Default: 2000)
If the Use dynamic Knowledge Base during extraction setting is selected the configured number also restricts the number of documents that are added to the specific dynamic knowledge base.
A large number of documents may cause a slow extraction rate so the project administrator needs to review the quantity at regular intervals.
- Use dynamic Knowledge Base during extraction
-
If this setting is enabled, a specific dynamic knowledge base is created by the Knowledge Base Learning Server for the documents marked for Extraction Online Learning in Validation, and this dynamic knowledge base is used next time extraction is performed. (Default: Selected)
When disabled, the project administration has to import and review the documents returned from online learning by Validation and update the project before any improvements are made.
- Automatic training after Validation
-
Select to automatically flag a document for Extraction Online Learning. When the document is flagged it can be imported to improve the project. (Default: Cleared)
If the Use dynamic Knowledge Base during extraction setting is selected a flagged document is added to the dynamic specific knowledge base and can be used during extraction processing.
However, you have to define fields in the Field details window that are monitored for flagging by selecting the Monitor for automatic learning setting. You can only monitor fields that are assigned to a trainable locator field. A document is used for Extraction Online Learning when the confidence of an extracted field is below a certain confidence level or field coordinates were changed during Validation or Thin Client Validation.
- Problem Reporting Settings
-
This group has the following settings:
- Standard Comments For Problem Reporting
-
This table contains a list of preconfigured comments available to users when they report a problem with a document in Validation.You can manage your comments by using the following buttons:
- Allow Validation users to type custom reasons
-
Select this setting if you want to allow Validation users to type in their own custom reason rather than use one of the predefined reasons configured in the Standard Comments For Problem Reporting table. (Default: Cleared)
The following buttons are available at the bottom of this window:
Button |
Description |
---|---|
OK |
Closes the window and saves your changes. |
Cancel |
Closes the window without saving your changes. |
![]() |
Displays the help for the open window. |
Related topics: