Any Self-Learning Base Extractor or Custom Extractorcan have the self-learning capability enabled. 'Base' Extractors cannot be self-learning as they are not customer-specific so controls are in place to ensure model regression does not occur.
The self-learning option ("Learn from Reviewed Documents") can be toggled under Collection settings.
When toggled 'on', all documents confirmed by a user from this Collection will be used in retraining for the Extractor attached to this Collection. This gives users ultimate control over what documents get fed into the training queue for a specific Extractor and means that test Collections can be used to test model performance or other features without impacting on the performance and accuracy of a given Extractor.
Updated 19 days ago