The integration of dependency relation classification and semantic role labeling using bilayer maximum entropy Markov models | |
Sun, Weiwei ; Li, Hongzhan ; Sui, Zhifang | |
2008 | |
英文摘要 | This paper describes a system to solve the joint learning of syntactic and semantic dependencies. An directed graphical model is put forward to integrate dependency relation classification and semantic role labeling. We present a bilayer directed graph to express probabilistic relationships between syntactic and semantic relations. Maximum Entropy Markov Models are implemented to estimate conditional probability distribution and to do inference. The submitted model yields 76.28% macro-average F1 performance, for the joint task, 85.75% syntactic dependencies LAS and 66.61% semantic dependencies F1. ? 2008.; EI; 0 |
语种 | 英语 |
内容类型 | 其他 |
源URL | [http://ir.pku.edu.cn/handle/20.500.11897/327599] |
专题 | 信息科学技术学院 |
推荐引用方式 GB/T 7714 | Sun, Weiwei,Li, Hongzhan,Sui, Zhifang. The integration of dependency relation classification and semantic role labeling using bilayer maximum entropy Markov models. 2008-01-01. |
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