C-rater: Automated scoring of short-answer questions

Abstract

C-rater is an automated scoring engine that has been developed to score responses to content-based short answer questions. It is not simply a string matching program - instead it uses predicate argument structure, pronominal reference, morphological analysis and synonyms to assign full or partial credit to a short answer question. C-rater has been used in two studies: National Assessment for Educational Progress (NAEP) and a statewide assessment in Indiana. In both studies, c-rater agreed with human graders about 84% of the time. © 2003 Kluwer Academic Publishers.