| In the Computer Assisted Assessment area,the techniques of the auto-assessment of the object questions,such as single choices,multiple choices and vacancy filling questions etc.,have been very perfect and been used in large-scaled testing systems.But,when refers to the subject questions,such as the term explanation,short answer questions,essay questions and compositions etc.their auto-assess techniques remain unperfected,because the subject questions' auto-assess techniques are restricted by the development of the techniques in Artificial Intelligence area,the Natural Language Understanding area and the Pattern Recognition area,so,there was no applied system in use.In China,the subject questions' assessment is still in manual.What's more,there are many object or subject factors that will influence the result,such as the cleanness of the student's papers,the beauty or ugliness of the student's handwriting,the teacher's mood etc.That brings down the justness of the competition between the students.The computer,however,is prior to human in processing speed,efficiency,precision and never be tired.What's more,there is no object or subject factor that can influence its work.So,it is very fit for the auto-assessment of the subjective questions.In this paper,we introduced the Chart algorithm for syntax analysis and the concept of single similar degree based on the theories of the fuzzy mathematics into the Subjective-Question-Autoassess-System.Facing the difficult problems of Chart algorithm for syntax analysis,such as ambiguities and efficiency,we have proposed to select the rule according to the function value when reductive each time.The principle is:Arrange in an order the rule dynamic grading according to the rule function value in the regular storehouse,analyze by having priority in depth,and choose the first syntax analysis tree as optimum seeking of tree.Then by analyzing the ways of the teacher assessment subjective, the concept of single similar degree based on the theories of the fuzzy mathematics is introduced,a subjective automated assessment algorithm is designed.The article expounds how to construct a Subjective-Question-Autoassess-System.We divide the system into four main tasks:word segment and sentence segment,syntax analysis,keyword extraction and sentence similarity computing.They have adopted the Maximum Match based approach algorithms,improved Chart algorithm separately and single similar degree.After we have analyzed them own characteristics,we provided the flow of algorithm,analysis tactics,the procedure of realization.Finally,we developed the system.The auto-assess result was pretty good for Computer Science and Technology. |