Study on Chinese question classification based on SVM multi-category classification

Wei Zhang; Liguo Duan; Junjie Chen

doi:10.1117/12.923769

13 January 2012 Study on Chinese question classification based on SVM multi-category classification

Wei Zhang, Liguo Duan, Junjie Chen

Proceedings Volume 8349, Fourth International Conference on Machine Vision (ICMV 2011): Machine Vision, Image Processing, and Pattern Analysis; 83493L (2012) https://doi.org/10.1117/12.923769
Event: Fourth International Conference on Machine Vision (ICMV 11), 2011, Singapore, Singapore

Abstract

Support vector machine (SVM) was initially used for binary classification. How to generalize the result of two-class classification to multi-class classification has been a problem which needs to be more investigated and studied. A general overview of existing representative methods for multi-category support vector machines was presented and their performances were compared in the paper. Then, the algorithms were applied in the Chinese question classification. Chinese question classification hierarchy and the feature selection of the question were also discussed in the paper. Then, The four algorithms of SVM multi-category classification were applied to Chinese question classification and some contrast experiments were done. The result of the experiments has shown that the binary-tree algorithm is more effective than the other algorithms in the Chinese question classification.

Citation Download Citation

Wei Zhang, Liguo Duan, and Junjie Chen "Study on Chinese question classification based on SVM multi-category classification", Proc. SPIE 8349, Fourth International Conference on Machine Vision (ICMV 2011): Machine Vision, Image Processing, and Pattern Analysis, 83493L (13 January 2012); https://doi.org/10.1117/12.923769

ACCESS THE FULL ARTICLE

INSTITUTIONAL
Select your institution to access the SPIE Digital Library.

SELECT YOUR INSTITUTION

PERSONAL
Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.

PERSONAL SIGN IN

No SPIE Account? Create one

PURCHASE THIS CONTENT

SUBSCRIBE TO DIGITAL LIBRARY

50 downloads per 1-year subscription

Members: $195

Non-members: $335 ADD TO CART

25 downloads per 1 - year subscription

Members: $145

Non-members: $250 ADD TO CART

PURCHASE SINGLE ARTICLE

Includes PDF, HTML & Video, when available