Main Aspects of Big Data Semantic Annotation

Abstract

Semantic annotations, due to their structure, are an in­teg­ral part of the effective solution of big data problems. However, the problem of defining semantic annotations is not trivial. Manual annotation is not acceptable for big data due to their size and heterogeneity, as well as the complexity and cost of the annotation process, the auto­ma­tic annotation task for big data has not yet decision. So, resolving the problem of semantic annotation requires modern mixed approaches, which would be based on and using the existing theoretical apparatus, namely methods and models of machine learning, statistical learning, wor­king with content of different types and formats, natural lan­guage processing, etc. It also should provide solutions for main annotation tasks: discovering and extracting en­ti­ties and relationships from content of any type and de­fi­ning semantic annotations based on existing sources of know­ledge (dictionaries, ontologies, etc.). The obtained an­notations must be accurate and provide a further op­por­tu­nity to solve application problems with the annotated data. Note that the big data contents are very different, as a result, their properties that should be annotated are very dif­ferent too. This requires different metadata to describe the data. It leads to large number of different metadata stan­dards for data of different types or formats appears. How­ever, to effectively solve the annotation problem, it is necessary to have a generalized description of the metadata types, and we have to consider metadata spe­ci­fi­city within this description. The purpose of this work is to define the general classification of metadata and de­ter­mi­nate common aspects and approaches to big data se­man­tic annotation.

Problems in programming 2020; 4: 22-33