@inproceedings{99aa60a9199a45f2a1033e43f136277f,
title = "Pattern-based extraction of addresses from web page content",
abstract = "Extraction of addresses and location names from Web pages is a challenging task for search engines. Traditional information extraction and natural processing models remain unsuccessful in the context of the Web because of the uncontrolled heterogenous nature of the Web resources as well as the effects of HTML and other markup tags. We describe a new pattern-based approach for extraction of addresses from Web pages. Both HTML and vision-based segmentations are used to increase the quality of address extraction. The proposed system uses several address patterns and a small table of geographic knowledge to hit addresses and then itemize them into smaller components. The experiments show that this model can extract and itemize different addresses effectively without large gazetteers or human supervision.",
keywords = "Address Extraction, Address Itemization, Web page Analysis",
author = "Saeid Asadi and Guowei Yang and Xiaofang Zhou and Yuan Shi and Boxuan Zhai and Jiang, \{Wendy Wen Rong\}",
year = "2008",
doi = "10.1007/978-3-540-78849-2\_41",
language = "English",
isbn = "3540788484",
series = "Lecture Notes in Computer Science (including subseries Lecture Notes in Artificial Intelligence and Lecture Notes in Bioinformatics)",
pages = "407--418",
booktitle = "Progress in WWW Research and Development - 10th Asia-Pacific Web Conference, APWeb 2008, Proceedings",
note = "10th Asia Pacific Conference on Web Technology, APWeb 2008 ; Conference date: 26-04-2008 Through 28-04-2008",
}