基于词聚类的依存句法分析

来源期刊:中南大学学报(自然科学版)2011年第7期

论文作者:袁里驰

文章页码:2023 - 2027

关键词:自然语言处理;词聚类;中心词驱动模型;句法分析统计模型

Key words:natural language processing; word clustering; head-driven parsing model; statistical Parsing model

摘    要:利用语义、语法等语言知识,对中心词驱动的句法分析模型规则进行分解和修改,结合分词、词性标注进行句法分析,提出一种可同时考虑多个语义依存关系的模型。利用互信息给出基于邻接关系、语义依存关系的2种词相似度定义,提出一种自下而上的分层聚类算法,以解决中心词驱动模型数据稀疏问题,用改进的句法分析模型进行句法分析实验。研究结果表明:模型精确率和召回率分别为88.14%和86.93%,综合指标比Collins头驱动句法分析模型的综合指标提高6.09%。

Abstract:

By incorporating linguistic features such as semantic dependency and syntactic relations, a novel statistical Parsing model was proposed. The model was constructed on cluster, and the problem of data sparseness was not serious. The model took advantage of a few semantic dependencies at the same time, and it was a parser based on lexicalized model. Experiments were conducted for the refined statistical parser. The results show that precision and recall are 88.14% and 86.93%, respectively, and comprehensive factor is improved by 6.09% compared with that of the head-driven parsing model.

相关论文

  • 暂无!

相关知识点

  • 暂无!

有色金属在线官网  |   会议  |   在线投稿  |   购买纸书  |   科技图书馆

中南大学出版社 技术支持 版权声明   电话:0731-88830515 88830516   传真:0731-88710482   Email:administrator@cnnmol.com

互联网出版许可证:(署)网出证(京)字第342号   京ICP备17050991号-6      京公网安备11010802042557号