Article Review: Text Similarity Techniques Used In Automated Short Answer Scoring (ASAS)

Abstract

In Automated short answer scoring systems, text similarity measurement plays an important role. it compares student's responses with reference response to indicate a final score based on the degree of similarity between the two answers. There have been many studies of text similarity and resulting in various approaches and algorithms. This paper investigates two majors of text similarity measurements, namely lexical and semantic similarity. The results of the investigation showed that the semantic similarity approach is more rational in subjective answers. While lexical similarity performs better and faster in objective answers.