跳到主要导航 跳到搜索 跳到主要内容

Learning to Surface Deep Web Content

  • SKLMS Lab

科研成果: 书/报告/会议事项章节会议稿件同行评审

摘要

We propose a novel deep web crawling framework based on reinforcement learning. The crawler is regarded as an agent and deep web database as the environment. The agent perceives its current state and submits a selected action (query) to the environment according to Q-value. Based on the framework we develop an adaptive crawling method. Experimental results show that it outperforms the state of art methods in crawling capability and breaks through the assumption of full-text search implied by existing methods.

源语言英语
主期刊名Proceedings of the 24th AAAI Conference on Artificial Intelligence, AAAI 2010
出版商AAAI press
1967-1968
页数2
ISBN(电子版)9781577354642
出版状态已出版 - 15 7月 2010
已对外发布
活动24th AAAI Conference on Artificial Intelligence, AAAI 2010 - Atlanta, 美国
期限: 11 7月 201015 7月 2010

出版系列

姓名Proceedings of the 24th AAAI Conference on Artificial Intelligence, AAAI 2010

会议

会议24th AAAI Conference on Artificial Intelligence, AAAI 2010
国家/地区美国
Atlanta
时期11/07/1015/07/10

学术指纹

探究 'Learning to Surface Deep Web Content' 的科研主题。它们共同构成独一无二的指纹。

引用此