AN IMPROVED MODEL OF MST FOR CHINESE DEPENDENCY PARSING

摘要：

　　In this paper,a Chinese dependency parsing method is proposed based on improved Maximum Spanning Tree (MST) Parser.Within this method,dependency direction discrimination model and head POS recognition model are used to modify the weights of directed edges in the MST model,and then the Eisner algorithm is used to search and generate the dependency trees.In this paper,the problems of dependency direction discrimination and head POS recognition are converted into sequence labeling; and the modeling is done by condition random fields.We tested our method on CoNLL 2009 Share Task,and the Unlabeled Attachment Score reached 86.27%.

关键词： Dependency parsing Maximum spanning tree Condition random fields

作者: Guiping Zhang Yan Wang Duo Ji

作者单位: Shen Yang Aerospace University,Research Center for Knowledge Engineering,Shen yang 110136,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: 1936-1940

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）