Novel rules for extracting the entities of entity relationship models

Abstract

Extracting entities from natural language text to design conceptual models of the entity relationships is not trivial and novice designers and students can find it especially difficult. Researchers have suggested linguistic rules/guidelines for extracting entities from natural language text. Unfortunately, while these guidelines are often correct they can, also, be invalid. There is no rule that is true at all times. This paper suggests novel rules based on the machine learning classifiers, the RIPPER, the PART and the decision trees. Performance comparison was made between the linguistic and the machine learning rules. The results shows that there was a dramatic improvement when machine learning rules were used.