[1]刘颖 韩杰 滕至阳.基于支持向量机的问句分析[J].计算机技术与发展,2007,(08):1-4.
　LIU Ying,HAN Jie,TENG Zhi-yang.Research of Question Analysis Based on Support Vector Machine[J].,2007,(08):1-4.
点击复制

基于支持向量机的问句分析()
分享到：

《计算机技术与发展》[ISSN:1006-6977/CN:61-1281/TN]

卷:
期数:
2007年08期
页码:
1-4
栏目:
智能、算法、系统工程
出版日期:
1900-01-01

文章信息/Info

Title:
Research of Question Analysis Based on Support Vector Machine
文章编号:
1673-629X（2007）08-0001-04
作者:
刘颖 韩杰 滕至阳
东南大学计算机科学与工程学院
Author(s):
LIU Ying;  HAN Jie;  TENG Zhi-yang
School of Computer Sci. and Eng. , Southeast University
关键词:
概念层次网络理论; 问句分类; 支持向量机; 中文信息处理; 问答系统
Keywords:
hierarchical network of concepts theory;  question catalog;  support vector machine;  Chinese information processing;  question answering system
分类号:
TP391.1
文献标志码:
A
摘要:
为提高问答系统对问句理解的准确率,以概念层次网络理论结合传统计算语言学为思路,提出了适用于限定领域中问句分析模型,根据限定领域的知识特点,设计了新的问句分类方法。在此问句分类方法的基础上,构建了基于支持向量机理论的问句分类器。在以实际教学过程中所收集的真实问句为问题集和训练集的测试中,取得了较好的实践效果
Abstract:
A novel, closed-domain oriented question analysis module based on hierarchical network of concepts and traditional computational linguistics is proposed to enhance the rate of accuracy of question interpretation of a question answering system. A new question catalog is developed on the basis of characteristics of closed- domain. A novel question classifier based on support vector machine is constructed on the grounds of this new catalog. The result of experiments tested on questions gathered during process of instruction shows better promise to this method

备注/Memo

备注/Memo:
国家“十五”重大科技攻关项目（2509000012）刘颖（1975-），男，江苏淮阴人，硕士，研究方向为嵌入式系统、自然语言理解等；滕至阳，教授，研究方向为人工智能、ICAI等
更新日期/Last Update: 1900-01-01