Combining constituent and dependency syntactic views for chinese semantic role labeling | |
Li, Shiqi ; Lu, Qin ; Zhao, Tiejun ; Liu, Pengyuan ; Li, Hanjing | |
2010 | |
英文摘要 | This paper presents a novel feature-based semantic role labeling (SRL) method which uses both constituent and dependency syntactic views. Comparing to the traditional SRL method relying on only one syntactic view, the method has a much richer set of syntactic features. First we select several important constituent-based and dependency- based features from existing studies as basic features. Then, we propose a statistical method to select discriminative combined features which are composed by the basic features. SRL is achieved by using the SVM classifier with both the basic features and the combined features. Experimental results on Chinese Proposition Bank (CPB) show that the method outperforms the traditional constituent-based or dependency-based SRL methods.; EI; 0 |
语种 | 英语 |
内容类型 | 其他 |
源URL | [http://ir.pku.edu.cn/handle/20.500.11897/329661] |
专题 | 信息科学技术学院 |
推荐引用方式 GB/T 7714 | Li, Shiqi,Lu, Qin,Zhao, Tiejun,et al. Combining constituent and dependency syntactic views for chinese semantic role labeling. 2010-01-01. |
个性服务 |
查看访问统计 |
相关权益政策 |
暂无数据 |
收藏/分享 |
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。
修改评论