Automated Chinese Essay Scoring Using Vector Space Models

摘要：

This paper presents experiments using several vector space models in Automated Essay Scoring (AES). Firstly, we compare four different Vector Space Models (VSM) which are the Word-based Vector Space Model (W-VSM), the Weight Adapted Wordbased Vector Space Model (WAW-VSM), the Latent Semantic-based Vector Space Model (LS-VSM) and the Sequence Latent Semantic-based Vector Space Model (SLSVSM). The results show that the WAW-VSM with the addition of word relation information is better than the W-VSM, while the SLS-VSM is also better than the LS-VSM by considering the sequence information in document representation. After that, we add some statistical surface features in the experiments. With the application of Support Vector Regression (SVR), the final machine score is generated. The correlation between the machine score and the human score reaches that between two human scores in average.

关键词： Automated Essay Scoring Vector Space Model Latent Semantic Analysis Word Similarity Sequence Information

作者: Xingyuan Peng Dengfeng Ke Zhenbiao Chen Bo Xu

作者单位: Digital Content Technology Research Center, Institute of Automation National Lab of Pattern Recognition, Institute of Automation Chinese Academy of Sciences, Beijing 10

会议类型: 国际会议

会议名称: 2010 4th International Universal Communication Symposium(第四届国际普遍交流学术研讨会 IUCS 2010)

会议地点: 北京

会议语种:英文

页码: 148-152

在线出版日期: 2010-10-18（万方平台首次上网日期，不代表论文的发表时间）