This paper is a result of a task that was presented to attendants of Keyword Search in Big Linked Data summer school, that was organized by Vienna University of Technology, under the Keystone COST action in the summer of 2017. It presents a specific approach to the classification via creation of minimal document surrogates based on the US National medical library’s MeSH ontology, which is derived from the Medical Subject Headings thesaurus. In a series of previously classified medically ...
... i et al., 2012) tested a few meth-
ods based on MeSH classification based on either MeSH ontology or the-
saurus. Created classifiers used:
– MeSH Thesaurus only (‘Thesaurus-oriented’ classifiers);
– Training set to build explicit models for each MeSH concept (‘Concept-
oriented’ classifiers);
– Manually ...
... on taxonomy from the MeSH ontology
and a rule-based system managing the appearance of terms related to con-
cepts from the MeSH ontology in the documents to be classified. The course
of the experiment can be divided into five follow-up steps.
1. Extraction of taxonomy from MeSH ontology using SPARQL ...
... predicates and objects of the MeSH 2016
ontology triple, whose concept is a part of (Figure 3). The query is illustrated
on the concept mesh2016:D049916.
PREFIX mesh2016: mesh/2016/>
SELECT DISTINCT ?predikat ?objekat
FROM mesh/2016>
WHERE mesh2016:D049916 ...
Mihailo Škorić, Mauro Dragoni. "Medical Domain Document Classification via Extraction of Taxonomy Concepts from MeSH Ontology" in Infotheca, Faculty of Philology, University of Belgrade (2019). https://doi.org/10.18485/infotheca.2019.19.1.3
