Open AccessAnswer Book Valuation Using Semantic Similarity
Author(s) -
P. Sunilkumar,
K.S. Sunil
Publication year - 2021
Publication title -
iop conference series. materials science and engineering
Language(s) - English
Resource type - Journals
eISSN - 1757-899X
pISSN - 1757-8981
DOI - 10.1088/1757-899x/1085/1/012018
Subject(s) - valuation (finance) , computer science , declaration , information retrieval , similarity (geometry) , semantic similarity , publication , artificial intelligence , accounting , programming language , political science , law , economics , image (mathematics)
Conventional examination systems are a tedious task for the universities and the faculties. It takes a lot of time and human effort for the valuation of the answer books, updation of the marks and the declaration of the results. Automation of descriptive answer book assessment would be useful for universities and academic institutions to simplify the valuation system to a large extend. It ensures a uniform valuation and also helps to publish the results without much delay after the examination. We design a system for automatic assessment of descriptive answer books of technical subjects. Semantic similarity is a metric used to assess the similarity between documents and it gives the degree of similarity as a numeric value. It can be used to value the students’ answer books by checking the similarity with original answers given in the answer key and then award appropriate marks.