Novel rules for extracting the entities of entity relationship models

Mussa Omar,Abdulrhman Alsheky,Balha Faiz

doi:10.51984/jopas.v20i2.1329

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.

Highlights

Creating an Entity Relationship Model (ERM) from requirements is frequently the first step in designing a database system, which is an important step in the software development life cycle
This paper suggests novel rules based on the machine learning classifiers, the RIPPER, the PART and the decision trees
Experiment and Results Discussion The purpose of the experiment is use machine learning classifiers for establishing a set of rules to be utilized for detecting entities of ERMs from natural language text

Summary

Introduction

Creating an Entity Relationship Model (ERM) from requirements is frequently the first step in designing a database system, which is an important step in the software development life cycle. The authors utilized decision tree classifiers, the PART and the RIPPER classifiers for developing a set of guidelines to be used for entity identification from natural language text. 4. Experiment and Results Discussion The purpose of the experiment is use machine learning classifiers for establishing a set of rules to be utilized for detecting entities of ERMs from natural language text.

Results

Conclusion