Grooper Consultant Training: Separation and Classification Training
October 20 - October 22$5,000
Separation and Classification Training
You have a bunch of loose pages. These pages make up documents. Those documents need to be put into distinct groups. That’s what separation and classification is for! Gooper’s robust document separation and classification techniques can turn almost any mess of paper into an organized document set.
This course aims to educate users on different methods available in Grooper to separate pages into document folders and classify those folders. Students will review the different Separation Providers, analyzing their uses and limitations. After separating pages into documents, students will learn different approaches to classifying those documents. These include training-based approaches, using Grooper’s machine learning capabilities to classify documents and rules-based approaches to identify documents using data extraction techniques. Finally, this course will delve into ESP Separation, a powerful way to separate and classify complex document sets with a variety of document types. A workshop session will be available at the end of the course to examine documents after training content is delivered. Students are encouraged to bring documents as well.
- Using Grooper’s Separation Providers, including:
- Control Sheet, Change In Value, Pattern Based, EPI, and Event Based
- Different classification techniques, their benefits, and limitations, including:
- Machine learning approaches
- “Rules-Based” pattern matching approaches
- Dealing with poor quality documents. Mitigating poor OCR to get better separation and classification results
- Building data extractors for classification purposes
- Students will analyze, review, and build Separation Profiles for a variety of document types and use cases.
- Students will configure Content Models to solve a variety of classification problems