Concept Extractor Suite - The Complete System for Metadata Management
Imagine having full bibliographic records built automatically. The Data Harmony Concept Extractor suite makes that possible. You choose the fields or data elements you need, and Access Innovations does the rest.
The Data Harmony Concept Extractor suite includes:
- Automatic Summarization - automatically summarizes documents saving time when constructing article summaries
- Metadata Extractor - automatically builds a document record, converting raw, unstructured, or semi-structured information into structured information
- Thesaurus Master - easy to use software for thesaurus and taxonomy management and construction
- M.A.I. (Machine Aided Indexer) - fast and efficient document indexing. Can be used to assist human indexers or for fast and accurate automatic indexing
- Entity Extractor - entity extraction extracts the people places and things as named entities from the full text of the articles and tags them as XML
These tools work together, taking full text documents in PDF, a Microsoft Office format (Word, Excel, PowerPoint), or Sun Open Office, and convert them to fully metatagged records. The resulting bibliographic citation with abstract and subject indexing from the thesaurus is then available as a full XML record for deposit in a database, Web CMS, or document management system.
Concept Extractor can be run in batch mode for large legacy sets of data or interactively as each item is submitted to the repository.
