一种基于粗糙集的大规模语料库语言学 知识发现.pdfVIP

　CN4321258/ TP 　　　计算机工程与科学 2004 年第 26 卷 第 5 期 　 　ISSN COMPUTER ENGINEERING SCIENCE 　Vol 126 ,No15 ,2004 　 ( ) 文章编号 2004 0520056206 一种基于粗糙集的大规模语料库语言学 X 　 知识发现模型 A Model for Linguistic Knowledge Discovery from Large2Scale Corpuses Based on Rough Set Techniques 陈清才 ,王晓龙 ,赵 　健 CHEN Qing2cai , WANG Xiao2long , ZHAO Jian ( 哈尔滨工业大学计算机科学与技术学院, 黑龙江 哈尔滨 150001) ( School of Computer Science and Technology , Harbin Institute of Technology , Harbin 150001,China) 摘 　要 :文中首先通过语言学特征表来对文本信息进行结构化处理 , 同时实现了对远距离约束的表 示 ;然后借助于面向个体的数据泛化算法来去除语言学特征表中的冗余信息 ,并利用规则抽取算法过滤 特征表中不一致的部分 ,从而为相应的自然语言处理任务建立了一个一致、高效的规则库。最后 ,本文 研究了模型在汉语词义排歧以及音字转换中的应用 ,在采用了动态规则平滑算法后 ,分别获得了 0. 93 和 0. 95 的判别精度以及0. 92和0. 89的覆盖率 ,这一结果显示模型具有很高的实用性。 Abstract :In the paper , a linguistic feature table (LFT) is first provided to structurize textural information and to represent long2distance constraints. Then , the redundant information in the LFT is wiped off by a kind of object2 oriented data generalization algorithm , inconsistent objects are filtered through the rule extraction algorithm and a consistent and efficient rule base is constructed for the NLP application. At last , the applications in Chinese word sense disambiguation and Chinese pinyin2to2character conversion are presented. In the case of introducing a dynamic rule smoothing algorithm , our experiment achieves 0. 93 and 0. 95 of decision precisions and 0. 92 and 0. 89 of rule recall rates with respect to these two applications , which shows the good performance of the model.