The following scenarios describe possible use cases for Eduction:
Use edktool to compile grammars, and test extraction on IDX, XML, or plain text documents.
Use the Eduction ACI server from a browser to identify employee names in a document.
Use Eduction to extract and compile a list of product names or company names from your data.
Use Eduction as a preprocessing tool to automatically extract entities from your documents and add them as metadata to your documents before indexing.
Use Eduction to extract common search phrases from documents before indexing, and tag the documents with this data.
Set up an Eduction task to extract different parts of your documents to different fields. For example, if your documents are letters, you can extract the name, address, and date from each document into predefined fields.
Use Eduction to extract information from the results of Optical Character Recognition.
Use the redaction feature to conceal sensitive information in your output, so that you can conform to data protection standards and use your records for multiple purposes.
The Eduction architecture supports the extraction of:
common entities, including place, personal names, and companies.
any basic entities you define using dictionaries or grammars.
complex entities you define (facts, events, relationships, and so on).