该文研究了通过作文词汇评分来实现汉语作文自动评分的新算法。在作文评分应与词汇评分高度相关的假设基础上,实现了这种关系的量化计算。该文从通用词表方法、常规方法以及提出的三种改进算法上进行方法性能的比较,并对比了E-rater作文评分系统中同样采用基于词汇方法的性能。实验结果表明,基于新的词汇评分的作文评分方法相关度①接近0.7的水平,高于E-rater中采用的基于词汇的方法的相关度。同时,这一方法的结果已经接近于人工作文评分的相关度。
Abstract
This paper studies new methods of automated Chinese essay scoring based on word scores. Under the hypothesis of the high correlation between the essay score and the scores of words in the essay, the equation of the relation is defined. The conventional methods and three enhanced methods are implemented to estimate the parameters of the equation. Compared with the e-raters methods, our new methods have a correlation close to 0.7, which demonstrates the performance of the latter is better. In addition, the performance of our methods is close to manual results.
Key wordsword scores; automated essay scoring
关键词
词汇评分 /
作文自动评分
{{custom_keyword}} /
Key words
word scores /
automated essay scoring
{{custom_keyword}} /
{{custom_sec.title}}
{{custom_sec.title}}
{{custom_sec.content}}
参考文献
[1] S. Dikli. An overview of automated scoring of essays[J]. Journal of Technology, Learning, and Assessment, 2006, 5(1): 1-35.
[2] 李亚男. 汉语作为第二语言测试的作文自动评分研究[D]. 北京: 北京语言大学, 2006.
[3] T. Landauer, D. Laham, P. Foltz. Automatic essay assessment[J]. Assessment in Education: Principles, Policy and Practice, 2003, 10(3): 295-309.
[4] 曹亦薇, 杨晨. 使用潜在语义分析的汉语作文自动评分研究[J]. 考试研究, 2007, 3 (1): 63-71.
[5] Y. Attali, J. Burstein. Automated essay scoring with e-rater v.2[J]. Journal of Technology, Learning, and Assessment, 2006, 4(3): 1-30.
[6] T. Ishioka, M. Kameda. Automated Japanese essay scoring system based on articles written by experts[C]//Proceedings of ACL. Sydney, Australia, 2006: 233-240.
[7] 彭恒利. 中国少数民族汉语水平等级考试[J]. 中国考试, 2005, 10:57-59.
{{custom_fnGroup.title_cn}}
脚注
{{custom_fn.content}}
基金
视听觉信息的认知计算(90820303);汉语考试中海量作文多层面全自动评分技术(61103152)
{{custom_fund}}