@inproceedings{2e8aa7900b2440d69aa1410bc46781da,
title = "Applying pattern mining to web information extraction",
abstract = "Information extraction (IE) from semi-structured Web documents is a critical issue for information integration systems on the Internet. Previous work in wrapper induction aim to solve this problem by applying machine learning to automatically generate extractors. For example, WIEN, Stalker, Softmealy, etc. However, this approach still requires human intervention to provide training examples. In this paper, we propose a novel idea to IE, by repeated pattern mining and multiple pattern alignment. The discovery of repeated patterns are realized through a data structure call PAT tree. In addition, incomplete patterns are further revised by pattern alignment to comprehend all pattern instances. This new track to IE involves no human effort and content-dependent heuristics. Experimental results show that the constructed extraction rules can achieves 97 percent extraction over fourteen popular search engines.",
keywords = "Information extraction, Multiple alignment, Pattern discovery, Semi-structured documents, Wrap-per generation",
author = "Chang, {Chia Hui} and Lui, {Shao Chen} and Wu, {Yen Chin}",
note = "Publisher Copyright: {\textcopyright} Springer-Verlag Berlin Heidelberg 2001.; 5th Pacific-Asia Conference on Knowledge Discovery and Data Mining, PAKDD 2001 ; Conference date: 16-04-2001 Through 18-04-2001",
year = "2001",
doi = "10.1007/3-540-45357-1_4",
language = "???core.languages.en_GB???",
isbn = "3540419101",
series = "Lecture Notes in Artificial Intelligence (Subseries of Lecture Notes in Computer Science)",
publisher = "Springer Verlag",
pages = "4--15",
editor = "David Cheung and Williams, {Graham J.} and Qing Li",
booktitle = "Advances in Knowledge Discovery and Data Mining - 5th Pacific-Asia Conference, PAKDD 2001, Proceedings",
}