Learning to surface deep web content

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

1 Scopus citations

Abstract

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.

Original languageEnglish
Title of host publicationAAAI-10 / IAAI-10 - Proceedings of the 24th AAAI Conference on Artificial Intelligence and the 22nd Innovative Applications of Artificial Intelligence Conference
PublisherAI Access Foundation
Pages1967-1968
Number of pages2
ISBN (Print)9781577354666
StatePublished - 2010
Event24th AAAI Conference on Artificial Intelligence and the 22nd Innovative Applications of Artificial Intelligence Conference, AAAI-10 / IAAI-10 - Atlanta, GA, United States
Duration: 11 Jul 201015 Jul 2010

Publication series

NameProceedings of the National Conference on Artificial Intelligence
Volume3

Conference

Conference24th AAAI Conference on Artificial Intelligence and the 22nd Innovative Applications of Artificial Intelligence Conference, AAAI-10 / IAAI-10
Country/TerritoryUnited States
CityAtlanta, GA
Period11/07/1015/07/10

Fingerprint

Dive into the research topics of 'Learning to surface deep web content'. Together they form a unique fingerprint.

Cite this