| 中文自动文摘在搜索引擎中的应用 |
| |
| 引用本文： | 董建设,任丽,周燕玲.中文自动文摘在搜索引擎中的应用[J].情报科学,2006,24(2):267-269,309. |
| |
| 作者姓名： | 董建设 任丽 周燕玲 |
| |
| 作者单位： | 兰州理工大学,计算机与通信学院,甘肃,兰州,730050 |
| |
| 摘 要： | 将自动文摘应用与搜索引擎系统，可以使用户更方便、直观地了解被命中网页的内容。本系统在实现基于网页的自动文摘时，针对Web文本的特点，采用了以统计为基础，统计和规则相结合的自动文摘生成策略，实现了HTML标记加权处理、中文文本切分和同义词分析，在此基础上完成了基于统计的文摘句初步提取和基于语用规则的进一步处理。
|
| 关 键 词： | 搜索引擎 自动文摘 语义分析 语用分析 |
| 文章编号： | 1007-7634（2006）02-0267-03 |
| 收稿时间： | 2005-06-15 |
| 修稿时间： | 2005-06-15 |
Application of Automatic Abstracting in Search Engine |
| |
| DONG Jian-she,REN Li,ZHOU Yan-ling.Application of Automatic Abstracting in Search Engine[J].Information Science,2006,24(2):267-269,309. |
| |
| Authors: | DONG Jian-she REN Li ZHOU Yan-ling |
| |
| Institution: | School of Computer and Communication, Lanzhou University of Technology, Lanzhou 730050, China |
| |
| Abstract: | Applying automatic abstracting to search engine can make it easier for user to find out the content of the web page which be voted. Aim at the webpage's characters, this system use a policy of automatic abstracting that statistic method combined with the method based on pragmatic rule. The system realized the weighting of HTML tags, the cutting of Chinese words and the treating of synonyms. On this foundation, this system completed drawing abstract sentence based on statistics preliminarily and the further filter based on pragmatics rule. |
| |
| Keywords: | search engine automatic abstracting semantic analysis pragmatic analysis |
| 本文献已被 CNKI 维普 万方数据 等数据库收录！ |
