@article{LI2009, 
author = {Guoliang LI and Jianhua FENG and Lizhu ZHOU},
title = {Keyword Searches in Data-Centric XML Documents Using Tree Partitioning},
year = {2009},
journal = {Tsinghua Science and Technology},
volume = {14},
number = {1},
pages = {7-18},
keywords = {keyword searches, extensive markup language (XML), self-integral trees, ranking, indexing},
url = {https://www.sciopen.com/article/10.1016/S1007-0214(09)70002-1},
doi = {10.1016/S1007-0214(09)70002-1},
abstract = {This paper presents an effective keyword search method for data-centric extensive markup language (XML) documents. The method divides an XML document into compact connected integral subtrees, called self-integral trees (SI-Trees), to capture the structural information in the XML document. The SI-Trees are generated based on a schema guide. Meaningful self-integral trees (MSI-Trees) are identified, which contain all or some of the input Keywords for the keyword search in the XML documents. Indexing is used to accelerate the retrieval of MSI-Trees related to the input keywords. The MSI-Trees are ranked to identify the top-k results with the highest ranks. Extensive tests demonstrate that this method costs 10-100 ms to answer a keyword query, and outperforms existing approaches by 1-2 orders of magnitude.}
}