Mark a new sample from the problems subset as complete
Unlike
Extraction
New Samples,
Problem
New Samples are not removed automatically from the
New
Samples document set. The best practice is to mark each sample document from the
Problems subset as complete after you add it to a training set. Once you mark a document complete,
the
Complete icon
is displayed in the
Trained column to indicate that the document no longer requires attention.
If necessary, you can filter your documents so that only those documents left to process are displayed.
You can mark one or more document from the Problems subset as complete by following these steps:
- Open the Documents window if it is not already open.
-
Select the
New Samples document subset.
The document set expands, the Problems document subset is selected by default, and the problem documents are displayed.
-
Optionally, add documents to the
Classification Set or the
Extraction Set as required.
When you add a document to a training set, the Complete icon
is displayed in the
Classification and
Extraction columns.
-
Select the completed documents, and on the Documents toolbar, select
Change State to Complete.
The Complete icon
is displayed in the
Trained column for each document selected.
- Optionally, filter the samples to exclude completed documents.
-
Optionally,
delete the completed sample documents.
The best practice is to remove all trained and complete documents from the Problems subset once they are added to their respective training sets. This is because the document information is now part of the training sets and the Generic Knowledge Base.
The selected documents are removed from the Problems document subset.