@inproceedings{7d865c0cd59c4434a69f36183df7c807,
title = "Approximate Membership Localization (AML) for web-based join",
abstract = "In this paper, we propose a search-based approach to join two tables in the absence of clean join attributes. Non-structured documents from the web are used to express the correlations between a given query and a reference list. To implement this approach, a major challenge we meet is how to efficiently determine the number of times and the locations of each clean reference from the reference list that is approximately mentioned in the retrieved documents. We formalize the Approximate Membership Localization (AML) problem and propose an efficient partial pruning algorithm to solve it. A study using real-word data sets demonstrates the effectiveness of our search-based approach, and the efficiency of our AML algorithm.",
keywords = "AML, Approximate join, Approximate membership location, Web-based join",
author = "Zhixu Li and Laurianne Sitbon and Liwei Wang and Xiaofang Zhou and Xiaoyong Du",
year = "2010",
doi = "10.1145/1871437.1871611",
language = "English",
isbn = "9781450300995",
series = "International Conference on Information and Knowledge Management, Proceedings",
pages = "1321--1324",
booktitle = "CIKM'10 - Proceedings of the 19th International Conference on Information and Knowledge Management and Co-located Workshops",
note = "19th International Conference on Information and Knowledge Management and Co-located Workshops, CIKM'10 ; Conference date: 26-10-2010 Through 30-10-2010",
}