CASIA OpenIR  > 模式识别国家重点实验室  > 自然语言处理
A Global Generative Model for Chinese Semantic Role Labeling
Yang HT(杨海彤); Zong, Chengqing
2014
会议名称Proceedings of The 3rd CCF Conference on Natural Language Processing & Chinese Computing
会议录名称Proceedings of The 3rd CCF Conference on Natural Language Processing & Chinese Computing
会议日期2014-11
会议地点Shen Zhen
摘要
The predicate and its semantic roles compose a unified entity that conveys the semantics of a given sentence. A standard pipeline of current approaches to semantic role labeling (SRL) is that for a given predicate in a sentence, we can extract features for each candidate argument and then perform the role classification through a classifier. However, this process totally ignores the integrality of the predicate and its semantic roles. To address this problem, we present a global generative model in which a novel concept called Predicate-Arguments-Coalition (PAC) is proposed to encode the relations among individual arguments. Owing to PAC, our model can effectively mine the inherent properties of predicates and obtain a globally consistent solution for SRL. We conduct experiments on the standard benchmarks: Chinese PropBank. Experimental results on a single syntactic tree show that our model outperforms the state-of-the-art methods.
关键词Global Generative Model
文献类型会议论文
条目标识符http://ir.ia.ac.cn/handle/173211/11860
专题模式识别国家重点实验室_自然语言处理
通讯作者Zong, Chengqing
推荐引用方式
GB/T 7714
Yang HT,Zong, Chengqing. A Global Generative Model for Chinese Semantic Role Labeling[C],2014.
条目包含的文件
文件名称/大小 文献类型 版本类型 开放类型 使用许可
A Global Generative (380KB)会议论文 开放获取CC BY-NC-SA浏览 请求全文
个性服务
推荐该条目
保存到收藏夹
查看访问统计
导出为Endnote文件
谷歌学术
谷歌学术中相似的文章
[Yang HT(杨海彤)]的文章
[Zong, Chengqing]的文章
百度学术
百度学术中相似的文章
[Yang HT(杨海彤)]的文章
[Zong, Chengqing]的文章
必应学术
必应学术中相似的文章
[Yang HT(杨海彤)]的文章
[Zong, Chengqing]的文章
相关权益政策
暂无数据
收藏/分享
文件名: A Global Generative Model for Chinese Semantic Role Labeling.pdf
格式: Adobe PDF
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。