C-rater: Automated scoring of short-answer questions

被引:152
作者
Leacock, C
Chodorow, M
机构
[1] Educ Testing Serv, Princeton, NJ 08541 USA
[2] CUNY Hunter Coll, New York, NY 10021 USA
来源
COMPUTERS AND THE HUMANITIES | 2003年 / 37卷 / 04期
关键词
automated scoring; content-based scoring; short answer scoring;
D O I
10.1023/A:1025779619903
中图分类号
TP39 [计算机的应用];
学科分类号
081203 ; 0835 ;
摘要
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.
引用
收藏
页码:389 / 405
页数:17
相关论文
共 16 条
[1]  
ABNEY S, 1996, P ESSLLI 96 ROB PARS
[2]  
[Anonymous], AUTOMATED ESSAY SCOR
[3]  
BURSTEIN J, 1999, DEPTH BREADTH SEMANT
[4]  
Cormen T. H., 2001, Introduction to Algorithms, V2nd
[5]  
Elliott S., 2003, AUTOMATED ESSAY SCOR
[6]  
Fellbaum C, 1998, LANG SPEECH & COMMUN, P1
[7]  
Fleiss J. L, 1981, STAT METHODS RATES P, P212
[8]  
KAPLAN RM, 1994, 0408 ETS
[9]  
KUD JM, 1994, P ED TEST SERV C NAT
[10]  
Landauer TK, 1997, PROCEEDINGS OF THE NINETEENTH ANNUAL CONFERENCE OF THE COGNITIVE SCIENCE SOCIETY, P412