loading page

Heritage Connector: A Machine Learning Framework for Building Linked Open Data from Museum Collections
  • Kalyan Dutia,
  • John Stack
Kalyan Dutia
Science Museum Group
Author Profile
John Stack
Science Museum Group
Author Profile

Abstract

As with almost all data, museum collection catalogues are largely unstructured, variable in consistency and overwhelmingly composed of thin records. The form of these catalogues means that the potential for new forms of research, access and scholarly enquiry that range across multiple collections and related datasets remains dormant. In the project Heritage Connector: Transforming text into data to extract meaning and make connections, we are applying a battery of digital techniques to connect similar, identical and related items within and across collections and other publications. In this paper we describe a framework to create a Linked Open Data knowledge graph (KG) from digital museum catalogues, connect entities within this graph to Wikidata, and create new connections in this graph from text. We focus on the use of machine learning to create these links at scale with a small amount of labelled data, on a mid-range laptop or a small cloud virtual machine. We publish open-source software providing tools to perform the tasks of KG creation, entity matching and named entity recognition under these constraints.

Peer review status:ACCEPTED

18 Dec 2020Submitted to Applied AI Letters
21 Dec 2020Submission Checks Completed
21 Dec 2020Assigned to Editor
06 Jan 2021Reviewer(s) Assigned
31 Jan 2021Review(s) Completed, Editorial Evaluation Pending
03 Feb 2021Editorial Decision: Revise Major
09 Mar 20211st Revision Received
10 Mar 2021Assigned to Editor
10 Mar 2021Submission Checks Completed
11 Mar 2021Reviewer(s) Assigned
01 Apr 2021Review(s) Completed, Editorial Evaluation Pending
01 Apr 2021Editorial Decision: Revise Minor
27 Apr 20212nd Revision Received
28 Apr 2021Assigned to Editor
28 Apr 2021Submission Checks Completed
28 Apr 2021Review(s) Completed, Editorial Evaluation Pending
28 Apr 2021Editorial Decision: Accept