Application researches of latent semantic analysis in Chinese essay auto scoring system construction

Computer Engineering and Applications ›› 2007, Vol. 43 ›› Issue (20): 177-180.

• 数据库与信息处理 • Previous Articles Next Articles

Application researches of latent semantic analysis in Chinese essay auto scoring system construction

LI Li，ZHANG Tai-hong

College of Computer and Information Engineering，Xingjian Agricultural University，Urumqi 830052，China

Received:1900-01-01 Revised:1900-01-01 Online:2007-07-11 Published:2007-07-11
Contact: LI Li

LSA在中文短文自动判分系统中的应用研究

李莉，张太红

新疆农业大学计算机与信息工程学院，乌鲁木齐 830052

通讯作者: 李莉

Abstract

Abstract: The basic idea of Latent Semantic Analysis（LSA） is described in the introduction of the paper.The application of LSA to the Chinese writing essays’ auto scoring is studied in this paper.The influence of machine auto scoring results of different data standard processing and different semantic space construction methods are compared basing on the analysis of 136 college students’ writing test paper.The effect of Singular Value Decomposition（SVD） and the rules for definition of the K numbers of singular values are discussed.In the last part of the paper，two teachers validate the results.It shows that it is feasible to score Chinese subjective test by machine auto scoring system.The method proposed in this paper offers a new option for variety test questions of auto test system.

Key words: Latent Semantic Analysis（LSA）, Singular Value Decomposition（SVD）, machine auto scoring in subjective test

摘要： 对潜在语义分析（Latent Semantic Analysis，LSA）的理论基础进行了介绍，研究了潜在语义分析在中文短文写作自动评分领域的应用方法。从136名大学生的短文写作试卷着手，对比了不同的语义空间构造方法和不同数据标准化方法对机器自动评分结果的影响，探讨了SVD的作用和奇异值个数K的取值规律，比较了LSA对不同类型学生的短文写作自动评分结果的差异。通过与两名教师对学生短文写作评分的比较表明，使用机器对主观题进行自动评分是可行的，该方法为自动化考试系统试题多样性提供了有效的解决方案。

关键词: 潜在语义分析, 奇异值分解, 主观题自动判分

LI Li，ZHANG Tai-hong. Application researches of latent semantic analysis in Chinese essay auto scoring system construction[J]. Computer Engineering and Applications, 2007, 43(20): 177-180.

李莉，张太红. LSA在中文短文自动判分系统中的应用研究[J]. 计算机工程与应用, 2007, 43(20): 177-180.

[1]	YANG Xinmin, DONG Hongbin, TAN Chengyu, ZHOU Wen. Dendritic Cell Model Using Singular Value Decomposition and Information Gain [J]. Computer Engineering and Applications, 2021, 57(15): 156-162.
[2]	CAO Hao, CHEN Lili, SI Jibing, REN Junlan. Singular Value Decomposition and Sparse Automatic Encoder for Bearing Fault Diagnosis [J]. Computer Engineering and Applications, 2019, 55(20): 257-262.
[3]	LIANG Xinyu1，2, WU Jiande1，2, HUANG Guoyong1，2, SUN Lei1，2. H∞ robust adaptive CKF algorithm used in GNSS/INS integrated navigation [J]. Computer Engineering and Applications, 2018, 54(9): 251-256.
[4]	LI Tianxue, WANG Jianping, ZHANG Minqing, KONG Yongjun. High fidelity reversible data hiding algorithm based on SVD compression [J]. Computer Engineering and Applications, 2018, 54(14): 115-119.
[5]	ZHENG Xiongfeng, DING Lixin, WAN Runze. User and product Attention mechanism based hierarchical BGRU model [J]. Computer Engineering and Applications, 2018, 54(11): 145-152.
[6]	FU Ying, WANG Xing, ZHOU Dongqing, FAN Xiangyu, ZHOU Yipeng. Recognition method of radar signal based on SVD of ambiguity function and improved S3VM algorithm [J]. Computer Engineering and Applications, 2017, 53(6): 264-270.
[7]	SUN Lei1，2, HUANG Guoyong1，2, LI Yue1，2. Exploration of improved strong tracking SVD-UKF used in BDS/INS integrated navigation [J]. Computer Engineering and Applications, 2017, 53(10): 225-229.
[8]	LIU Yan, TANG Wei. De-noising algorithm of AMSVD and its application in PQMD [J]. Computer Engineering and Applications, 2016, 52(23): 255-259.
[9]	CUI Yeqin1, GAO Jianguo1, DING Guochao2. Noise suppression method for seismic signals based on LLE reconstruction and SVD decomposition [J]. Computer Engineering and Applications, 2016, 52(15): 266-270.
[10]	PU Ling. Random noise reduction for seismic data based on Locally Linear Embedding [J]. Computer Engineering and Applications, 2015, 51(9): 213-216.
[11]	WANG Zijia1，2, FAN Yugang1，2, WU Jiande1，2. Application of feature extraction based on S energy spectrum in bearing fault diagnosis [J]. Computer Engineering and Applications, 2015, 51(18): 261-265.
[12]	BU Fanyu1，2, CHEN Zhikui1, ZHANG Qingchen1. Incremental updating method for big data feature learning [J]. Computer Engineering and Applications, 2015, 51(12): 21-26.
[13]	WANG Kun1, WU Zongyong2, HUANG Wenfang3. Improved algorithm based on Singular Value Decomposition in wideband spectrum sensing [J]. Computer Engineering and Applications, 2015, 51(12): 213-218.
[14]	LI Fan1，2, JIN Minglu1, LIU Ji3. Distributed singular value decomposition least squares estimation algorithm [J]. Computer Engineering and Applications, 2014, 50(3): 6-12.
[15]	XU Chenkai, GAO Maoting. Improved ART2 neural network for text clustering based on LSA [J]. Computer Engineering and Applications, 2014, 50(24): 133-138.

Application researches of latent semantic analysis in Chinese essay auto scoring system construction

LSA在中文短文自动判分系统中的应用研究

PDF

Knowledge

Abstract

Cite this article

share this article

References

Related Articles 15

Recommended Articles

Metrics