基于配价结构的词汇化句法分析模型

来源期刊:中南大学学报(自然科学版)2012年第5期

论文作者:袁里驰

文章页码:1808 - 1813

关键词:配价结构;语义依存关系;中心词驱动;句法分析模型

Key words:valence structure; semantic dependency; head-driven; syntactic parsing model

摘    要:基于“配价”是汉语词语的一个比较本质的特点,一旦1个词语的配价结构确定下来,它应该和怎样的词进行搭配就比较清楚,从而也可以比较直接地导出句子的结构,为此,结合中心词驱动句法分析模型,提出基于配价结构的词汇化句法分析模型,引入丰富的语义信息如语义依存信息和配价结构等语义搭配信息,并用改进的句法分析模型进行句法分析实验。实验结果表明:模型的精确率和召回率分别为88.65%和87.26%,综合指标F与Collins的中心词驱动句法分析模型的相比提高6.51%。

Abstract: Based on the fact that “valency” is an essential semantic feature of Chinese words, once the valency of word is determined, the collocation of the word is clear, and the sentence structure can be directly derived, a syntactic parsing model combining valence structure with head-driven statistical syntactic parsing models was purposed, which incorporates rich semantic information including semantic dependency and semantic collocation. Experiments were conducted for the refined statistical parser. The results show that using refined statistical parser can achieve 88.65% precision and 87.26% recall, comprehensive index F is improved by 6.51% compared with the head-driven parsing model introduced by Collins.

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