The Community for Technology Leaders
Asian Language Processing, International Conference on (2009)
Singapore
Dec. 7, 2009 to Dec. 9, 2009
ISBN: 978-0-7695-3904-1
pp: 28-33
ABSTRACT
Similarity computing of question is one of the important basis issues in the field of natural language processing, which was widely used in the Q&A system, and other areas such as question classification. In this paper, a method is presented that the keywords are extracted and then the similarity of keywords is calculated, and the similarity of sentences is the weighted average of similarity between keywords. A related experiment about simple questions has been done with the improved method based on the HowNet and syntactic analysis so that they can be applied to calculate the similarity of simple questions, and the accuracy rate reaches 83%. The experimental result shows that the method based on the HowNet and syntactic analysis is feasible to calculate the similarity between simple questions.
INDEX TERMS
CITATION
Han Yanhua, Shi Shuicai, Lv Xueqiang, Zhou Zhibin, "Similarity Computing Between Simple Questions Based on HowNet and Syntactic Analysis", Asian Language Processing, International Conference on, vol. 00, no. , pp. 28-33, 2009, doi:10.1109/IALP.2009.15
91 ms
(Ver 3.3 (11022016))