Method and Research on Chinese Predicate Recognition Based on Feature

被引：0
|
作者：
Wang, Chengmin [1 ]
Peng, Jun [1 ]
机构：
[1] Chongqing Univ Sci & Teclmol, Coll Elect Infomat Engn, Chongqing, Peoples R China
来源：
2010 8TH WORLD CONGRESS ON INTELLIGENT CONTROL AND AUTOMATION (WCICA) | 2010年
关键词：
Natural Language Processing; Shallow Paring; Predicate recognition;
D O I：
10.1109/WCICA.2010.5554788
中图分类号：
TP [自动化技术、计算机技术];
学科分类号：
0812 ;
摘要：
This paper puts forward a method of Chinese predicate recognition based on the features study, And according to the sentence's predicate center coming out of features, we obtain the characteristic knowledge of the predicate based on the language bank of artificial welled-marks, and make use of characteristic knowledge to identify predicate. Finally, In the open test the accuracy rate of Chinese predicate recognition closes to 840% and in the closed test the accuracy rate of Chinese predicate recognition closes to 86%.
引用
收藏
页码：5698 / 5701
页数：4
相关论文
共 7 条
  • [1] [Anonymous], 2007, P 2007 JOINT C EMP M
  • [2] [龚小谨 Gong Xiaojin], 2003, [中文信息学报, Journal of Chinese Information Processing], V17, P7
  • [3] Hong-lin SUN, 2000, CONT LINGUISTICS, V2, P74
  • [4] Igo S., 2008, P 23 NATL C ARTIFICI, P1458
  • [5] Luo Z.S., 1994, J CHINESE INFORM PRO, V8, P1
  • [6] Surdeanu M., 2008, Proceedings of the Twelfth Conference on Computational Natural Language Learning, CoNLL 2008, Manchester, UK, August 16-17, 2008, P159, DOI DOI 10.3115/1596324.1596352
  • [7] Zhi-fang SUI, 1998, J PEKING U SCI EDITI, V34, P221
1