On the Effectiveness of Using Syntactic and Shallow Semantic Tree Kernels for Automatic Assessment of Essays
Yllias Chali, Sadid A. Hasan · International Joint Conference on Natural Language Processing · 2013
This paper is concerned with the problem of automatic essay grading, where the task is to grade student written essays given course materials and a set of humangraded essays as training data. Latent Semantic Analysis (LSA) has been used extensively over the years to accomplish this task. However, the major limitation of LSA is that it only retains the frequency of words by disregarding the word sequence, and the syntactic and semantic structure of texts. As a remedy, we propose the use of syntactic and shallow semantic tree kernels for grading essays. Experiments suggest that syntactic and semantic structural information can significantly improve the performance of the state-of-the-art LSAbased models for automatic essay grading.