Title :
Automated Marking System for Short Answer examination (AMS-SAE)
Author :
Aziz, Mohd Juzaiddin Ab ; Ahmad, Fatimah Dato ; Ghani, Abdul Azim Abdul ; Mahmod, Ramlan
Author_Institution :
Comput. Sci. Dept, Univ. Kebangsaan Malaysia, Bangi, Malaysia
Abstract :
Short answers essay typed examination requires the students to write their answers in short sentences. Marking the short answers essay typed examination requires lecturers to compare the similarity of sentences from the answer scripts and marking scheme. Sentence similarity is defined as sentences that have similar meaning but they are different because of the words used or their construction structure. Automatic Marking System for Short Answers Examination (AMS-SAE) is a system that has been developed to grade students´ answers based on the given marking scheme. Marks are given to the essays based on the representation of the Grammatical Relations (GRs) extracted from the sentences. The average point different between the marks computed by AMS-SAE and human are 0.049, 0.028 and 0.18. The results show that the scores are low and AMS-SAE could award similar marks as the human awarded.
Keywords :
educational administrative data processing; natural language processing; text analysis; automated marking system; grammatical relations; sentence similarity; short answer examination; short answers essay typed examination; Application software; Computer science; Education; Failure analysis; History; Humans; Industrial electronics; Information technology; Testing; Writing; Malay sentences; grammatical relations;
Conference_Titel :
Industrial Electronics & Applications, 2009. ISIEA 2009. IEEE Symposium on
Conference_Location :
Kuala Lumpur
Print_ISBN :
978-1-4244-4681-0
Electronic_ISBN :
978-1-4244-4683-4
DOI :
10.1109/ISIEA.2009.5356500
