Towards a methodology for the semi-automatic generation of scientific knowledge graphs from XML documents



Hannah, G ORCID: 0000-0002-3218-4559, Payne, TR ORCID: 0000-0002-0106-8731, Tamma, V ORCID: 0000-0002-1320-610X, Mitchell, A, Piercy, E and Konev, B ORCID: 0000-0002-6507-0494
(2023) Towards a methodology for the semi-automatic generation of scientific knowledge graphs from XML documents. In: The 18th International Workshop on Ontology Matching, 2023-11-7 - 2023-11-7, Athens, Greece.

[img] PDF
Towards_a_methodology_for_the_semi_automatic_generation_of_scientific_knowledge_graphs_from_XML_documents__V2_.pdf - Other

Download (213kB) | Preview

Abstract

Robots used in analytical laboratories, such as those at Unilever, generate vast amounts of log data. This log data is typically stored in semi-structured formats (e.g. XML) according to some standard schema, e.g. the Analytical Information Markup Language (AnIML). Representing this data in a structured format such as a knowledge graph would allow for a more consistent data interpretation, as the relationships between concepts would be formalised in an ontology; consequently making the process of complex data analysis simpler for the scientists involved. We propose a semi-automatic pipeline that exploits the inherent structure of XML schemata, as well as previously represented domain knowledge, to create a knowledge graph that represents log data with its relevant metadata. We utilise ontology alignment techniques to identify related concepts in different ontologies, and therefore provide additional context when predicting the property linking two classes while building the graph.

Item Type: Conference or Workshop Item (Unspecified)
Uncontrolled Keywords: Ontology alignment, knowledge graph generation, XML
Divisions: Faculty of Science and Engineering > School of Electrical Engineering, Electronics and Computer Science
Depositing User: Symplectic Admin
Date Deposited: 16 Nov 2023 08:25
Last Modified: 22 Jan 2024 03:04
Related URLs:
URI: https://livrepository.liverpool.ac.uk/id/eprint/3176822