Highly accurate SVM model with automatic feature selection for word sense disambiguation  

作　　者：WangHao ChenGuilin XuLianxian 

机构地区：[1]DepartmentofComputerScienceandTechnology,ShanghaiJiaotongUniversity,Shanghai200030,P.R.China [2]MotorolaChinaResearchCenter,Shanghai200030,P.R.China

出　　处：《Journal of Systems Engineering and Electronics》2004年第4期723-727,共5页系统工程与电子技术（英文版）

摘　　要：A novel algorithm for word sense disambiguation(WSD) that is based on SVM model improved with automatic feature selection is introduced. This learning method employs rich contextual features to predict the proper senses for specific words. Experimental results show that this algorithm can achieve an execellent performance on the set of data released during the SENSEEVAL-2 competition. We present the results obtained and discuss the transplantation of this algorithm to other languages such as Chinese. Experimental results on Chinese corpus show that our algorithm achieves an accuracy of 70.0% even with small training data.

分 类 号：TP181[自动化与计算机技术—控制理论与控制工程]