| 基于组合验证的Web页面抽取算法研究 |
| |
| 引用本文： | 耿耘,蒋严冰,郭岩,刘悦,余钧,程学旗.基于组合验证的Web页面抽取算法研究[J].江西师范大学学报(自然科学版),2013,0(2):142-147. |
| |
| 作者姓名： | 耿耘 蒋严冰 郭岩 刘悦 余钧 程学旗 |
| |
| 作者单位： | 北京大学软件与微电子学院,北京100190;中国科学院计算技术研究所,北京100101；北京大学软件与微电子学院,北京,100190；中国科学院计算技术研究所,北京,100101 |
| |
| 摘 要： | 通过研究抽取算法的本质和抽取算法之间的关系,对抽取算法的互补性进行分析,提出了一种多算法组合验证机制,该机制能检测出抽取算法的错误,并通过结合动态阈值调整的方法,提高抽取算法的抽取准确率.
|
| 关 键 词： | 信息抽取 组合验证 阈值 多算法 |
Research of Information Extraction Algorithm Based on Compositional Verification |
| |
| GENG Yun,JIANG Yan-bing,GUO Yan,LIU Yue,YU Jun,CHENG Xue-qi.Research of Information Extraction Algorithm Based on Compositional Verification[J].Journal of Jiangxi Normal University (Natural Sciences Edition),2013,0(2):142-147. |
| |
| Authors: | GENG Yun JIANG Yan-bing GUO Yan LIU Yue YU Jun CHENG Xue-qi |
| |
| Institution: | 1.School of Software and Microelectronics,Peking University,Beijing 100190,China; 2.Institute of Computing Technology,Chinese Academy of Science,Beijing 100101,China) |
| |
| Abstract: | The nature of universal web-information retrieval algorithm has been investigated,and a frame of cross-validation mechanism which could detect failure of the retrieval process has been proposed.After then,the performance by dynamically adjust threshold value of each algorithm has been improved. |
| |
| Keywords: | information extraction cross validation threshold value multi-algorithm |
| 本文献已被 CNKI 等数据库收录！ |
| 点击此处可从《江西师范大学学报(自然科学版)》浏览原始摘要信息 |
| 点击此处可从《江西师范大学学报(自然科学版)》下载免费的PDF全文 |
|
