Automatic Subject Heading Extraction (ASHE) improves the discoverability of books that have not been fully cataloged by using natural language processing to extract terms and concepts for the automatic recognition of subject headings in library materials. Using lookup and scoring algorithms, ASHE successfully identifies medical subject headings. Future work for this project might include incorporation of other ontologies and vocabularies, such as Library of Congress subject headings and refinements to natural language processing.

Project Team: 

Betsy Eggleston
Director of Collections & Knowledge Management
Countway Library of Medicine

Jonathan Kennedy
Senior Software Engineer
Center for Biomedical Informatics
Countway Library of Medicine

Peter Rolla
Information Acquisitions & Management Librarian
Countway Library of Medicine

Juliane Schneider
Metadata Librarian
Countway Library of Medicine