Natural language understanding for grading essay questions in Persian language

Abstract

many intelligent systems are intended to communicate with users through natural language. Understanding the natural language by the computer is one of the most essential operations in natural language processing. One of the applications of natural languages is in the exams having essay questions. The objective of this paper is to propose a method for designing an examiner machine and creating an intelligent evaluator to grade the users' given answers to the essay questions. Algorithms such as "phrase structure" are weak at natural language processing in "free word order languages" such as Persian. The recommended method in this paper is based on "dependency grammar" and is applicable for various natural languages. Reduction in evaluation time and increase in the accuracy are advantages of the proposed method. © Springer-Verlag 2013.