Machine learning for production of Dewey Decimal

BRYGFJELD, Svein Arne and WETJEN, Freddy and WALSØE, André (2018) Machine learning for production of Dewey Decimal. Paper presented at: IFLA WLIC 2018 – Kuala Lumpur, Malaysia – Transform Libraries, Transform Societies in Session 115 - Subject Analysis and Access.

Bookmark or cite this item: http://library.ifla.org/id/eprint/2216
[img]
Preview
Language: English (Original)
Available under licence Creative Commons Attribution.

Abstract

Machine learning for production of Dewey Decimal

Based on Open Source software and existing metadata and content, the National Library of Norway has carried out a series of experiments to study automatic classification of articles based on the Dewey Decimal Classification system. Various platforms and models for machine learning has been used. The results indicate machine learning is a suitable environment for semi-automated or fully automated production of DDC. Furthermore, they show that training of machine learning platforms may be enforced by using artificial documents.

FOR IFLA HQ (login required)

Edit item Edit item
.