Dissertation > Excellent graduate degree dissertation topics show

Subjective questions scoring algorithm model

Author: TanDongChen
Tutor: ChenWenYu
School: University of Electronic Science and Technology
Course: Computer Software and Theory
Keywords: Chinese words segmentation finite state machine subjective questions automatic scoring text classification decision tree
CLC: TP391.1
Type: Master's thesis
Year: 2011
Downloads: 55
Quote: 0
Read: Download Dissertation

Abstract


With the development of information technology, computer applications have penetrated into the way of working, living and learning in all aspects. Informatization examination required to process different kinds of questions automatically without human intervention. Currently, the Chinese examination system can only process the objective questions such as choice questions and true or false questions, while the subjective scoring cannot be achieved automatically. The reason is that Chinese subjective questions automatic scoring algorithm involves natural language processing, pattern matching, and artificial intelligence and other fields of in-depth study. And the Chinese system itself is complicated and open. To achieve the automatic understanding of Chinese, we need deeper research.Chinese words segmentation is the basis for Chinese natural language processing and directly affects the efficiency and precision of top applications. Automatic subjective scoring model based on Chinese word segmentation.This thesis study technique related to Chinese words segmentation in depth first. The three types of segmentation method are analyzed deeply, and then compare their advantages and disadvantages. Summarizes the impact of Chinese words segmentation system accuracy of the ambiguity problem and named entity recognition problem. With the idea of finite state machine and Chinese words segmentation we propose the word segmentation algorithm based on two level indexes dictionary. And combine the K-shortest path algorithm to achieve the Chinese word. Our algorithm adopts N-gram model to process ambiguity and named entity recognition, and has achieved good recognition results.The thesis proposed a Chinese automated scoring model based on the text classification model and Chinese words segmentation. Using the HIT Thesaurus Lin to calculate the texts similarity as the condition attributes of the classifier. We also considered some superficial similarities of the text as features. Through the use of machine learning we adopt ID3 algorithm to construct decision tree classifiers, using the students’scores as classification categories. Finally, the automatic scoring reduced to input the student answer to the decision tree and the tree decide what score should be marked.Compared with the manual scoring process, we find that our model is feasible and effective and in line with manual marking process.

Related Dissertations

  1. Research on Text Classification Based on Biomimetic Pattern Recongnition,TP391.1
  2. Tourism Comments on the Internet’s Semantic Analysis and Usefulness Research,TP391.1
  3. Fault Diagnosis Method Based on Support Vector Machine,TP18
  4. Formalization-based Methed to Generate Test Sequence of UML,TP311.53
  5. Design and Development of Teaching Quality Assessment System Based on Data Mining,TP311.13
  6. Based on Data Distribution Characteristics of Text Classification,TP391.1
  7. Research on Ontology-based Scientific Papers of Chinese Classification,TP391.1
  8. Chinese Keyword Extraction Method Based on Word Span and Its Application in Text Classification,TP391.1
  9. Research on Application of Fuzzy Clustering and Decision Tree Classification Algorithm in Higher Vocational Students’ Employment,TP399-C1
  10. Research and Implementation of Community-based Medical Management System Based on SOA Architecture,TP311.52
  11. Research on Improved K Neighbor Support Vector Machine Algorithm Faced Text Classification,TP391.1
  12. Research on the Application of Data Mining Technology in the Regulating Matriculation for Postgraduate,TP311.13
  13. The Research and Implementation of Data Mining Technology in the Electronic Bulletin Board System Environment,TP311.13
  14. Data Mining Application in E-government OA System,TP311.13
  15. Text based on SVM multi-class classification,TP391.1
  16. IKE protocol robustness testing technology research,TP393.04
  17. Heuristic Mode Research of Decision Tree and Its Application in Attribute Reduction,TP18
  18. Information Extraction and Change Research of the Wetlands Along the Yangtze River and Lakes in Anqing,X37
  19. Information Geometry Based Pure High-order Interaction Model and Its Applications,TP391.1
  20. Research on Certification Examination Affairs Management System,TP311.52
  21. The Chinese Text Categorization Research Based on Support Vector Machine and Clustering Algorithm,TP391.1

CLC: > Industrial Technology > Automation technology,computer technology > Computing technology,computer technology > Computer applications > Information processing (information processing) > Text Processing
© 2012 www.DissertationTopic.Net  Mobile