@inbook{78cba1c8c6dc4c78a288bb7863a75e62,
title = "An efficient algorithm for clustering XML schemas",
abstract = "Schema clustering is important as a prerequisite to the integration of XML schemas. This paper presents an efficient method for clustering XML schemas. The proposed method first computes similarities among schemas. The similarity is defined by the size of the common structure between two schemas under the assumption that the schemas with less cost to be integrated are more similar. Specifically, we extract one-to-one matchings between paths with the largest number of corresponding elements. Finally, a hierarchical clustering method is applied to the value of similarity. Experimental results with many XML schemas show that the method has performed better compared with previous works, resulting in a precision of 98% and a rate of clustering of 95% in average.",
author = "Rhim, {Tae Woo} and Lee, {Kyong Ho} and Ko, {Myeong Cheol}",
year = "2004",
doi = "10.1007/978-3-540-30480-7_38",
language = "English",
series = "Lecture Notes in Computer Science (including subseries Lecture Notes in Artificial Intelligence and Lecture Notes in Bioinformatics)",
publisher = "Springer Verlag",
pages = "372--377",
editor = "Xiaofang Zhou and Orlowska, {Maria E.} and Stanley Su and Papazoglou, {Mike P.} and Jeffery, {Keith G.}",
booktitle = "Lecture Notes in Computer Science (including subseries Lecture Notes in Artificial Intelligence and Lecture Notes in Bioinformatics)",
address = "Germany",
}