Automated Essay Evaluation Augmented with Semantic Coherence Measures

Manual grading of students´ essays is a time-consuming, labor-intensive and expensive activity for educational institutions. It is nevertheless necessary since essays are considered to be the most useful tool to assess learning outcomes. Automated essay evaluation represents a practical solution to this task, however, its main weakness is predominant focus on vocabulary and text syntax, and limited consideration of text semantics. In this work, we propose an extension to existing automated essay evaluation systems that incorporates additional semantic attributes. We design the novel attributes by transforming sequential parts of an essay into the semantic space and measuring changes between them to estimate coherence of the text. The resulting system (called SAGE - Semantic Automated Grader for Essays) achieves significantly higher grading accuracy compared with 8 other state-of-the-art automated essay evaluation systems.