CORC  > 兰州理工大学  > 兰州理工大学  > 计算机与通信学院
Research of applying chain conditional random fields to semantic role labeling
Li, Ming; Wang, Yabin; Nian, Fuzhong; Wang, Xuyang
2009
会议日期November 30, 2009 - December 1, 2009
会议地点Wuhan, China
关键词Feature extraction Knowledge acquisition Semantics Conditional random field Conditional Random Fields(CRFs) Long-distance dependencies Precision and recall Prepositional phrase Relationship labeling Semantic role labeling Syntactic dependency trees
卷号1
DOI10.1109/KAM.2009.210
页码351-354
英文摘要The Conditional Random Fields (CRFs) only can deal with the sequence data of Markov property. And it can not realize the relationship labeling with more fine structure between semantic roles. An approach to semantic role labeling (SRL) based on Chain Conditional Random Fields (CCRFs) Model was proposed. The long-distance dependencies between different state variants were handled effectively via labeling Hierarchical Dependencies and Brother Dependencies of syntactic dependency tree. Moreover, some new combinative features and prepositional phrase also were added though taking advantages of any features can be added in CRFs model. The experiments were implemented on CoNLL 2008 Shared Task. The results indicate the proposed method can improve precision and recall rate of the system. © 2009 IEEE.
会议录2009 2nd International Symposium on Knowledge Acquisition and Modeling, KAM 2009
会议录出版者IEEE Computer Society
语种英语
内容类型会议论文
源URL[http://ir.lut.edu.cn/handle/2XXMBERH/116697]  
专题计算机与通信学院
兰州理工大学
作者单位School of Computer and Communication, Lanzhou University of Technology, Lanzhou, China
推荐引用方式
GB/T 7714
Li, Ming,Wang, Yabin,Nian, Fuzhong,et al. Research of applying chain conditional random fields to semantic role labeling[C]. 见:. Wuhan, China. November 30, 2009 - December 1, 2009.
个性服务
查看访问统计
相关权益政策
暂无数据
收藏/分享
所有评论 (0)
暂无评论
 

除非特别说明,本系统中所有内容都受版权保护,并保留所有权利。


©版权所有 ©2017 CSpace - Powered by CSpace