一种基于汉语隐喻依存句法树的嵌入式树匹配算法  

An Embedded Tree Matching Algorithm Based on Metaphorical Dependency Structure

作　　者：李剑锋[1] 杨芸[1] 周昌乐[1] 

机构地区：[1]厦门大学信息科学与技术学院,福建厦门361005

出　　处：《厦门大学学报（自然科学版）》2008年第4期500-504,共5页Journal of Xiamen University：Natural Science

基　　金：国家自然科学基金(60373080)资助

摘　　要：提出了一种基于汉语隐喻依存句法树的嵌入式树匹配算法,旨在发掘给定语句中所有可能存在隐喻关系的句法依存结构模式,即从隐喻依存模式库中寻找出所有能够嵌入目标依存句法树的模式,同时记录下对应的节点匹配结果.模式库由预先存入的从大规模隐喻句中抽象出来的标准化依存句法树组成.算法采用自上而下和自下而上回溯修正相结合的办法,实现了依存模式的精确匹配.测试结果表明,本算法能够准确无误的找出依存模式库中能够嵌入目标树的所有规则树,实现精确匹配的同时准确记录了每个节点的对应匹配结果,算法保证了较高的运行效率.This paper proposed an embedded dependency tree matching algorithm oriented to Chinese metaphor processing,aimed to find in a given sentence all the dependency relations that most probably occur in metaphors,that was to find out all the rule trees embedded in the given dependency tree, and at the same time record the matching results of corresponding nodes. The metaphoric dependency relations were derived from a large structured metaphor corpus, formalized as dependency trees and saved in a tree bank. The main process was top-down searching and bottom-up amending,and the test results showed that the algorithm could expectantly and efficiently find out accurate dependency relations and record the matching results.

关 键 词：树匹配 依存树 规则匹配 隐喻信息处理 

分 类 号：TP391[自动化与计算机技术—计算机应用技术]