Entity Extraction Scripts configuration

Entity Extraction Scripts (EESs) are used to configure ETA to extract complex items of information from text. EESs are composed in the ETA Configuration User Interface.

EESs contain lists of Rules. Rules are formed of a Matching Pattern and a set of Output Phrases. Rules operate in sequence to extract whatever information is required from text.

EES scripts can be triggered to run only if a document has a particular tag. Documents can be tagged automatically with ETA's built-in tagger/classifier.

EESs can take advantage of other configuration capabilities in ETA:

Figure 1: ETA EES configuration page

What you can do with Entity Extraction Scripts

Entity Extraction Scripts are a highly productive tool for configuring ETA to extract specific information from text.

Example applications include:

Figure 2: Entity Extraction Scripts applied to extract metadata from OCR-ed archival patents