STUDIES ON AUTOMATIC RECOGNITION OF PREPOSITION BAS USAGES BASED ON STATISTICS

摘要：

　　Researching on automatic recognition of prepositions usages is one of the important contents of the Chinese function words Knowledge Corpus.Aiming at the low recognition probability problem for some high-fiequency usages with rule-based method of preposition usages recognition,this paper proposed automatically recognizing of preposition usages based on statistics.Three statistical models,that is CRF、ME and SVM,were used to label preposition BAs usages on the tagged corpus of Peoples Daily (February,March,April of 2000).The experiment of statistical methods was done for preposition BA.And the final results showed that in general automatic recognition of preposition BAs usages based on statistics was better than that of rule-based method of preposition BAs usages recognition.

关键词： Chinese function work Usage description Conditional random fields Maximum entropy automatic recognition

作者: Lingling Mu Yiya Pang Hongying Zan

作者单位: School of Information Engineering,Zhengzhou University,Zhengzhou 450001,China

会议类型: 国际会议

会议名称: 2012 2nd IEEE International Conference on Cloud Computing and Intelligence Systems (2012年第2届IEEE云计算与智能系统国际会议(IEEE CCIS2012))

会议地点: 杭州

会议语种:英文

页码: 1875-1879

在线出版日期: 2012-10-30（万方平台首次上网日期，不代表论文的发表时间）