Data on structured documents generally exists in a predictable format from one document to the next. While information may change from document to document, presentation and labelling of that information is generally consistent. By no means does that mean extracting the data from them is always simple. Poor form design, differences in format, inconsistencies in data formatting, and other idiosyncrasies and oddities provide challenges to extracting data from structured and semi-structured documents.

This course aims to educate users on different methods to configure data extraction for structured and semi-structured documents. This course will focus heavily on data modeling of document sets, using extractor techniques to target, collate, and populate results.