Title :
Research on Chinese Question Classification Based on Hownet and Dependency Parsing
Author :
Zhang Wei ; Chen Junjie ; Niu Yanqing
Author_Institution :
Inf. Center, Shanxi Med. Coll. for Continuing Educ., Taiyuan, China
Abstract :
Question classification is an important part of Chinese question answering system, and the result of question classification directly affects the quality of question answering. This paper presents a new method on feature extraction for question classification. HowNet and dependency parsing are used in this new method. The classification experimental results using SVM classifier have shown that the model proposed in the paper is effective in improving question classification accuracy.
Keywords :
feature extraction; pattern classification; question answering (information retrieval); support vector machines; thesauri; Chinese question answering system; Chinese question classification; Hownet; SVM classifier; dependency parsing; feature extraction; Accuracy; Education; Feature extraction; Information retrieval; Semantics; Support vector machines; Syntactics;
Conference_Titel :
Intelligent Systems and Applications (ISA), 2011 3rd International Workshop on
Conference_Location :
Wuhan
Print_ISBN :
978-1-4244-9855-0
Electronic_ISBN :
978-1-4244-9857-4
DOI :
10.1109/ISA.2011.5873388
