Relation-Wise Automatic Domain-Range Information Management for Knowledge Entries

摘要

Relations play a vital role on knowledge construction and maintenance thereof. They for example connect domain type entities to range type entities, like the relation born in connects some Persons to some Places. Over any dataset, the domain-range information is used to maintain data consistency. Therefore, we see that knowledge construction frameworks sometime engage costly Knowledge Engineers to define the domain-range information in form of a schema or an ontology. We also see that frameworks that hold such defined domain-range information, often do not follow them strictly. In the worst case some frameworks do not even allow to define a domain-range, rather they just gather the knowledge entries. One reason of not defining the domain-range information is that it is costly. On the other hand, the reason for not following the domain-range constraint is that the most of them are either manual or semi-automatic, therefore they face adaptation difficulty. In this research, we propose a relation-wise machine learning model that can define and validate domain-range information automatically. The initial experiment shows that the proposed framework performs promisingly.