A Simulated Shallow Dependency Parser Based onWeighted Hierarchical Structure Learning

摘要：

In the past years much research has been done on data-driven dependency parsing and performance has increased steadily.Dependency grammar has an important inherent characteristic,that is,the nodes closer to root usually make more contribution to audiences than the others.However,that is ignored in previous research in which every node in a dependency structure is considered to play the same role.In this paper a parser based on weighted hierarchical structure learning is proposed to simulate shallow dependency parsing,which has the preference for nodes closer to root during learning.The experimental results show that the accuracies of nodes closer to root axe improved at the cost of a little decrease of accuracies of nodes far from root.

作者: Zhiming Kang Chun Chen Jiajun Bu Peng Huang Guang Qiu

作者单位: College of Computer Science,Zhejiang University,Hangzhou,China

会议类型: 国际会议

会议名称: 4th Asia Information Retrieval Symposium(AIRS 2008)(第四届亚洲信息检索研讨会)

会议地点: 哈尔滨

会议语种:英文

页码: 484-489

在线出版日期: 2008-01-16（万方平台首次上网日期，不代表论文的发表时间）