Grooper 21.00.0082 is available as of 12-12-2023! Check the  Downloads Discussion  for the release notes and to get the latest version.
Grooper 23.1.0016 is available as of 03-15-2024! Check the  Downloads Discussion  for the release notes and to get the latest version.
Grooper 23.00.0042 is available as of 03-22-2024! Check the Downloads Discussion for the release notes and to get the latest version.

Lexical and Visual Classification Combo Possible?

How can I set up a batch process to perform Lexical Classification and then perform Visual Classification on documents that were not classified by Lexical Classification?

Answers

  • BradleyBradley Posts: 94 ✭✭✭
    Because training data is stored on the Content Model along with your document types and data model(s), you can only choose one type of Classification. The training data between these two types of classification are like comparing oranges to apples; they are two entirely different algorithms when Classification is used.

    You could try to create two Content Models, one with Lexical training and the other with Visual training but you will be performing double the work on everything.

    Normally, if you are seeing many pages or documents failing to classify, the best practice is to spend more time improving the classification training by training more samples rather than try to configure some environment with two Content Models working in tandem. That approach would become difficult to manage as they grow in complexity.
  • GrooperGuruGrooperGuru Posts: 481 admin
    Check with @The Chuck , but I believe I saw something a few days ago in an upcoming dev release that would allow something like this to potentially be done. Let us know what you find out.
    Matt Harrison
    Product Manager
    mharrison@bisok.com
Sign In or Register to comment.