|Table of Contents|

[1] Liu Jiangang, Zhen Yuqi, Chen Meihua, Jiang Hao, et al. A study on the feasibility of CET oral testbased on automatic essay marking [J]. Journal of Southeast University (English Edition), 2012, 28 (4): 410-414. [doi:10.3969/j.issn.1003-7985.2012.04.007]
Copy

A study on the feasibility of CET oral testbased on automatic essay marking()
基于作文自动评分的大学英语口语评估系统可行性
Share：

Journal of Southeast University (English Edition)[ISSN:1003-7985/CN:32-1325/N]

Volumn:
28
Issue:
2012 4
Page:
410-414
Research Field:
Publishing date:
2012-12-30

Info

Title:
A study on the feasibility of CET oral testbased on automatic essay marking
基于作文自动评分的大学英语口语评估系统可行性
Author(s):
Liu Jiangang1, Zhen Yuqi1, Chen Meihua1, Jiang Hao2, Zhao Li3
1School of Foreign Languages, Southeast University, Nanjing 210096, China
2School of Computer Science and Engineering, Southeast University, Nanjing 210096, China
3School of Information Science and Engineering, Sou
刘健刚1, 郑玉琪1, 陈美华1, 姜浩2, 赵力3
1东南大学外国语学院, 南京 210096; 2东南大学计算机科学与工程学院, 南京 210096; 3东南大学信息科学与工程学院, 南京 210096
Keywords:
reliability and validity;  spoken document and textual document;  automatic essay marking
可信度和有效度;  口头言语记录和文字言语记录;  作文自动评分
PACS:
H319.3
DOI:
10.3969/j.issn.1003-7985.2012.04.007
Abstract:
This paper discusses the approach to the CET(college English test)oral test based on automatic essay marking(AEM). The reliability and validity arouses a dispute on Internet-based CET(iB-CET)oral test in China, leading to the penetration into oral test contents in dialogue, description or comment, and question answering. Then, a probe into transformation from a spoken document into a textual document is touched on a conversion ratio of 72% adopted at the present time, being a necessary hypothesis for AEM to be carried forward. Afterwards, this paper focuses on the pipeline in AEM with the content features and the language itself, which is established in two different models in marking for extraction and detection. Through experiments, this paper reveals the fact that an iB-CET oral test can be performed perfectly in the pipeline of spoken documents transformed into textual documents which can be automatically marked. Hence the design of the iB-CET oral test reaches its reliability and validity.
论述了作文自动评分系统平台上大学英语口语测试的实现途径.英语口语测试的可信度和有效度向中国当今的大学英语口语机考提出了挑战, 涉及机考英语口语测试是否需要还原传统的对话、叙述或评述、问答问题三大评估内容.首先简述了口头言语转化文字言语实现概率(72%)的现况, 并以此为自动评分的前提设想.其次, 设想了大学英语口语测试的实现途径, 即在口头言语转化为文字后, 应用作文自动平分对话语进行口语测试系统的2种建模:言语内容检测模型和语言本身检测模型.通过实验, 论证了运用作文自动评分系统平台进行大学英语口语测试的可实现性, 即实现了首先借助语音识别技术将口头言语转化为文字言语, 然后进行文字言语评估的自动评分.这种基于作文自动评分的大学英语口语测试系统建模研究和试验揭示了我国大学英语口语机考的可信度和有效度.

References:

[1] Yang Huizhong. The 15 years of CET and its impact on teaching [J]. Journal of Foreign Languages, 2003, 145(3): 21-29.(in Chinese)
[2] Liu Jiangang, Dong Jing. A study on language identification in call English oral test[J]. Chinese Journal of Electron Devices, 2011, 34(4): 482-484.(in Chinese)
[3] Bachman L, Paulmer A. In language testing in practice[M]. Oxford: Oxford University Press, 1996:25-26.
[4] Yang Jingpeiyi. A critical review of college English spoken test(CET-SET)[J]. Journal of Kunming University, 2010, 32(1): 135-137.(in Chinese)
[5] Gong Li, Liang Weiqian, Ding Yuguo. Feasibility study and practice of machine scoring of repetition question in large-scaled English oral test[J]. Computer-Assisted Foreign Language Education, 2009(02): 10-15.(in Chinese)
[6] Chen Xiaoya, Li Aijun, Sun Guohua. Phonetic research orientating speech technology[C]//The 6th National Conference on Man-Machine Speech Communication(NCMMSC6). Shenzheng, China, 2001:65-72.
[7] Favre B, Grishman R, Hillard D, et al. Punctuating Speech for Information Extraction[C]//IEEE International Conference on Acoustic, Speech and Signal Processing. Las Vegas, NV, USA, 2008:5013-5016.
[8] Matsoukas S, Bulyko I, Xiang B, et al. Integrating speech recognition and machine translation [C]//IEEE International Conference on Acoustic, Speech and Signal Processing. Honolulu, HI, USA, 2007:1281-1284.
[9] Fang Hongfeng, Feng Jiali, Wei Mengyun, et al. English pronunciation transform English character software actualize[J]. Journal of Haibin Engineering University, 2006, 27(Sup): 584-586.(in Chinese)
[10] Li li, Yu Yibao. Voice conversion using spectrum with super-segment prosody features[J]. Signal Processing, 2012, 28(2):289-294.(in Chinese)
[11] Ding Wangdao. A handbook of writing—revised English edition[M]. Beijing: Foreign Languages Learning and Research Publisher, 1994:151-153.
[12] Jiang Hao, Huang Guoqiang, Liu Jiangang. The research on CET automated essay scoring based on data mining[C]//International Conference on Advances in Computer and Education Applications(CSE 2011). Qiangdao, China, 2011: 100-105.
[13] Tao Huang. The research on CET automated essay scoring[D]. Nanjing: School of Computer Science and Engineering, Southeast University, 2011.(in Chinese)
[14] Wen Qiufang. Spoken and written English corpus of Chinese learners [M]. Beijing: Foreign Languages Learning and Research Press, 2009.(in Chinese)

Memo

Memo:
Biography: Liu Jiangang(1959—), male, associate professor, jhonliunj@163.com.
Foundation items: The Humanities and Social Sciences Project granted from the Ministry of Education in China(No.10YJA740061, 11YJA740121), the Teaching Reform Key Project under Educational Section of Jiangsu Province(No.2011JSJG453), Southeast University Teaching Reform Project for Graduates(No.2010-54), Southeast University Teaching Reform Project for Post-Graduates(No.KJGKT12-06), the Natural Science Foundation of Jiangsu Province(No.BK2008354), the National Natural Science Foundation of China(No.6550181821, 60975017).
Citation: Liu Jiangang, Zhen Yuqi, Chen Meihua, et al. A study on the feasibility of CET oral test based on automatic essay marking.[J]. Journal of Southeast University(English Edition), 2012, 28(4):410-414.[doi:10.3969/j.issn.1003-7985.2012.04.007]
Last Update: 2012-12-20