@inproceedings{765545b767904bb381b178c739934cac,
title = "Document versioning using feature space distances",
abstract = "The automated analysis of documents is an important task given the rapid increase in availability of digital texts. In an earlier publication, we had presented a framework where the edit distances between documents was used to reconstruct the version history of a set of documents. However, one problem which we encountered was the high computational costs of calculating these edit distances. In addition, the number of document comparisons which need to be done scales quadratically with the number of documents. In this paper we propose a simple approximation which retains many of the benefits of the method, but which greatly reduces the time required to calculate these edit distances. To test the utility of this method, the accuracy of the results obtained using this approximation is compared to the original results.",
keywords = "Data mining, Information retrieval, String matching, Text processing, Versioning",
author = "Woon, \{Wei Lee\} and Wong, \{Kuok Shoong Daniel\} and Zeyar Aung and Davor Svetinovic",
note = "Publisher Copyright: {\textcopyright} Springer International Publishing Switzerland 2014.; 21st International Conference on Neural Information Processing, ICONIP 2014 ; Conference date: 03-11-2014 Through 06-11-2014",
year = "2014",
doi = "10.1007/978-3-319-12640-1\_59",
language = "British English",
series = "Lecture Notes in Computer Science (including subseries Lecture Notes in Artificial Intelligence and Lecture Notes in Bioinformatics)",
publisher = "Springer Verlag",
pages = "487--494",
editor = "Loo, \{Chu Kiong\} and Yap, \{Keem Siah\} and Wong, \{Kok Wai\} and Andrew Teoh and Kaizhu Huang",
booktitle = "Neural Information Processing - 21st International Conference, ICONIP 2014, Proceedings",
address = "Germany",
}