@inproceedings{eaf420440d0747e6ae0648feafd4989e,
title = "Similarity join on XML based on k-generation set distance",
abstract = "Similarity join is applied very widely nowadays since data items representing the same real-world objects may be different due to various conventions. Another reason for similarity join is that the efficiency of traditional methods is really low. Therefore, a method with both high efficiency and high join quality is in need. In the paper, we put forward two new edit operations (reversing and mapping) together with related algorithms concerning similarity join based on the new defined measure. In our method, computing tree edit distance is replaced by computing k-generation set distance between trees. The join process is simplified largely by applying the new method. The time complexity of our method is O(n 2 ), where n is the tree size. We have proved that our method owns some advantages over others. And it can be scaled to large data sets as well.",
keywords = "Similarity join, XML, k-generation set distance, new edit operations",
author = "Yue Wang and Hongzhi Wang and Yang Wang and Hong Gao",
year = "2012",
doi = "10.1007/978-3-642-28635-3\_11",
language = "英语",
isbn = "9783642286346",
series = "Lecture Notes in Computer Science (including subseries Lecture Notes in Artificial Intelligence and Lecture Notes in Bioinformatics)",
pages = "124--135",
booktitle = "Web-Age Information Management - WAIM 2011 International Workshops",
note = "Int. Workshops on Web-Age Information Management, WAIM 2011: 1st Int. Workshop on Web-Based Geographic Information Management, WGIM 2011, 3rd Int. Workshop on XML Data Management, XMLDM 2011, 1st Int. Workshop on Social Network Analysis, SNA 2011 ; Conference date: 14-09-2011 Through 16-09-2011",
}