Generation and evaluation of linked data derived from information extraction methodologies

Abstract

By employing the extensible knowledge graph curation and analysis platform called Whyis, we can validate the constructed interactions discovered by our workflow in comparison to interactions stated in a domain-specific assertion database. Assessment of this data flow showcase the associated benefits, difficulties, precision, and potential usages alongside established ontologies. The data workflow implemented in this study provides an innovative approach for knowledge discovery, connectivity, and curation of information using a linked data methodology and assertion-based evaluation criteria.

Many approaches currently exist in the pursuit of knowledge representation from unstructured documents. With the extensive amount of information available, the need to derive a common meaning behind data has become more prevalent than ever before. In this thesis, we develop a workflow to support knowledge extraction and representation of data from the biomedical domain. To determine the hidden meaning behind text, we utilize popular Information Extraction methods to extract events from biomedical papers and store the output from these methods into a combined textual object and annotation representation format. This data is converted into an RDF Graph format based on groundings to scientific ontologies and provenance semantics.