New approaches to the ontology alignment and identity resolution problems

This paper describes approaches to the vocabulary normalization and identity resolution problems arising during the use of the LOD datasets to populate the content of scholarly knowledge bases. We have proposed new heuristics, using additional information extracted from full text sources of data. The first heuristics uses the full record track of a person and the second one uses self-citation networks. The dataset of the Open Archive of the Russian Academy of Sciences and several bibliographic datasets are used as test examples.