Automatic assessment of students’ free-text answers underpinned by the combination of a BLEU-inspired algorithm and latent semantic analysis

Abstract

In previous work we have proved that the BLEU algorithm (Papineni et al. 2001), originally devised for evaluating Machine Translation systems, can be applied to assessing short essays written by students. In this paper we present a comparative evaluation between this BLEU-inspired algorithm and a system based on Latent Semantic Analysis. In addition we propose an effective combination schema for them. Despite the simplicity of these shallow NLP methods, they achieve state-of-theart correlations to the teachers’ scores while keeping the language-independence and without requiring any domain specific knowledge.