| 汉语定义语句的抽取方法 |
| |
| 引用本文： | 张寅生.汉语定义语句的抽取方法[J].计算机与数字工程,2011(10):45-47,112. |
| |
| 作者姓名： | 张寅生 |
| |
| 作者单位： | 中国科学技术信息研究所 北京 100038 |
| |
| 摘 要： | 该文介绍了在汉语文本中抽取定义语句的方法。方法的主要特点是：给定被定义的词汇（字符串）,应用Bo-yer-Moore算法查找该串在文本中的位置,继而在该句子中查找符合定义特征的谓词。在这个工作基础上,根据谓词字符串的特征排除谓词歧义,并按照句法分析的结果对定义语句修饰谓词的不同语法单元进行识别,从而实现了基于字符串和语法特征的识别的定义语句抽取。
|
| 关 键 词： | 知识抽取 信息抽取 汉语句子识别 定义语句 Boyer-Moore算法 自然语言理解 |
Extraction of Chinese Sentences for Definition |
| |
| Zhang Yinsheng.Extraction of Chinese Sentences for Definition[J].Computer and Digital Engineering,2011(10):45-47,112. |
| |
| Authors: | Zhang Yinsheng |
| |
| Affiliation: | Zhang Yinsheng(Institute of Scientific & Technical Information of China,Beijing 100038) |
| |
| Abstract: | Using Boyer-Moore algorithm and grammar parsing technology,the paper studies extracting the Chinese sentences,which make some definitions,in texts.In the work,defined words,verbs and some functional phrases for definition are recognized so a more precise extractions are completed,and some words which might make incorrect extractions are avoided. |
| |
| Keywords: | knowledge extraction information extraction Chinese sentence recognition definition recognition Boyer-Moore algorithm natural language processing |
| 本文献已被 CNKI 维普 万方数据 等数据库收录！ |
