How can I manage the entities that a machine learning annotator has learned.
I want to manage the entities that a machine learning annotator has.
Because I want an application to show only the documents associated with entities the M/L annotator has learned.
Not only because the M/L annotator is going to learn more and more things but also because the standards of filtering come from the entities of M/L annotator itself, it's meaningless filtering documents at the crawling session.
So I want to know that are there ways to manage the entities of the M/L annotator.
So I have a few questions.
How can I make a facet including whole entities of M/L annotator so that when the facet is chosen by one then the one can see the documents that has something to do with M/L annotator has learned.
Can I use or customize M/L annotator inside of the Content Analytics Studio? Or at least can I check or see some contents of M/L annotator in Content Analytics Studio? For example by using the PEAR file?
Can I extract entities of the M/L annotator inside of the pipeline by using the custom annotator written by Java code?
Are there any other ways to achieve what I want? Any ideas would be pleasurable. For examples, Can it be achieved by programming language such as Java? Can it be done by using API? If so, How should I use the API?