The automatic extraction of entities and their types from text, coupled with entity linking to LOD datasets, are fundamental challenges for the evolution of the Semantic Web. In this paper, we describe an approach to automatically process natural language definitions to (a) extract entity types and (b) align those types to the DOLCE+DUL ontology. We propose SPARQL patterns based on recurring dependency representations between entities and their candidate types. For the alignment subtask, we essentially rely on a pipeline of strategies that exploit the DBpedia knowledge base and we discuss some limitations of DBpedia in this context.
CITATION STYLE
Haidar-Ahmad, L., Font, L., Zouaq, A., & Gagnon, M. (2016). Entity typing and linking using SPARQL patterns and DBpedia. In Communications in Computer and Information Science (Vol. 641, pp. 61–75). Springer Verlag. https://doi.org/10.1007/978-3-319-46565-4_5
Mendeley helps you to discover research relevant for your work.