@inproceedings{28c26daeb6094944b8d5cced90220c71,
title = "Siphon++: A hidden-web crawler for keyword-based interfaces",
abstract = "The hidden Web consists of data that is generally hidden behind form interfaces, and as such, it is out of reach for traditional search engines. With the goal of leveraging the high-quality information in this largely unexplored portion of theWeb, in this paper, we propose a new strategy for automatically retrieving data hidden behind keyword-based form interfaces. Unlike previous approaches to this problem, our strategy adapts the query generation and selection by detecting features of the index. We describe a preliminary experimental evaluation which shows that our strategy is able to to obtain coverages that are higher than those of previous approaches that use a fixed strategy for query generation.",
keywords = "Hidden-Web crawler, Online databases",
author = "Karane Vieira and Luciano Barbosa and Juliana Freire and Altigran Silva",
year = "2008",
doi = "10.1145/1458082.1458279",
language = "English (US)",
isbn = "9781595939913",
series = "International Conference on Information and Knowledge Management, Proceedings",
pages = "1361--1362",
booktitle = "Proceedings of the 17th ACM Conference on Information and Knowledge Management, CIKM'08",
note = "17th ACM Conference on Information and Knowledge Management, CIKM'08 ; Conference date: 26-10-2008 Through 30-10-2008",
}