@INPROCEEDINGS{StoilosGeletaEtAl18,
AUTHOR = {Stoilos, G. and Geleta, D. and Wartak, S. and Hall, S. and Khodadadi, M. and Zhao, Y. and Alghamdi, G. and Schmidt, R. A.},
TITLE = {Methods and Metrics for Knowledge Base Engineering and Integration},
BOOKTITLE = {9th Workshop on Ontology Design and Patterns (WOP 2018)},
SERIES = {CEUR Workshop Proceedings},
VOLUME = {2195},
PUBLISHER = {CEUR-WS.org},
PAGES = {72--86},
URL = {http://www.cs.man.ac.uk/~schmidt/publications/StoilosGeletaEtAl18.html},
ABSTRACT = {
Today a wealth of knowledge and data are distributed using
Semantic Web standards. Especially in the (bio)medical domain several
sources like the SNOMED CT, NCI, MedDRA, MeSH, ICD-10 ontologies, 
and many more are distributed in RDF and OWL. These can be
aligned and integrated in order to create one large medical Knowledge
Base. However, integrating different and largely heterogeneous sources
is far from trivial. First, although distributed in OWL many of the 
ontologies may not strictly follow the semantics of subClassOf as originally
intended for faceted search or use as thesauri. Second, even when they
do follow strict ontological guidelines, different ontologies may 
conceptualise the same domain in radically different ways. Analysing and 
understanding these sources before integrating them is highly beneficial. Third,
monitoring and understanding how the structure of the Knowledge Base
changes (evolves) after the integration is also crucial since changes to
its structure may affect applications that are built on top of it. In the
current paper we report on our Knowledge Base construction pipeline
which is based on ontology integration. We focus on the various metrics,
techniques, and tools we have developed in order to assist in achieving
this large-scale integration task. Our work was motivated by the need
for a medical Knowledge Base to be used to support digital healthcare
services developed at Babylon Health. We present results on the metrics
used to analyse various sources and the results of running the pipeline
on several medical ontologies.
}
}