Using machine-readable text as a source of novel vocabulary to update the Dewy Decimal classification

Caroline Jean Godby, Ray Reighart

Abstract


A technique is presented for automatically importing novel and emergent vocabulary into the Dewey Decimal Classification (DDC) from a domain-specific corpus of machine-readable text using insights from recent work by computational linguistics on word sense disambiguation. Results show that most of the vocabulary is mapped to the DDC hierarchy that is most appropriate for characterizing the domain.

Full Text:

PDF


DOI: http://dx.doi.org/10.7152/acro.v9i1.12746