@inproceedings{ccb9c7f420d041858a0f303666e5c767,
title = "An algorithm for segmenting categorical time series into meaningful episodes",
abstract = "This paper describes an unsupervised algorithm for segmenting categorical time series. The algorithm first collects statistics about the frequency and boundary entropy of ngrams, then passes a window over the series and has two “expert methods” decide where in the window boundaries should be drawn. The algorithm segments text into words successfully in three languages. We claim that the algorithm finds meaningful episodes in categorical time series, because it exploits two statistical characteristics of meaningful episodes.",
author = "Paul Cohen and Niall Adams",
note = "Publisher Copyright: {\textcopyright} Springer-Verlag Berlin Heidelberg 2001.; 4th International Conference on Intelligent Data Analysis, IDA 2001 ; Conference date: 13-09-2001 Through 15-09-2001",
year = "2001",
doi = "10.1007/3-540-44816-0_20",
language = "English (US)",
isbn = "3540425810",
series = "Lecture Notes in Computer Science (including subseries Lecture Notes in Artificial Intelligence and Lecture Notes in Bioinformatics)",
publisher = "Springer-Verlag",
pages = "198--207",
editor = "Frank Hoffmann and Gabriela Guimaraes and Hand, {David J.} and Niall Adams and Douglas Fisher",
booktitle = "Advances in Intelligent Data Analysis - 4th International Conference, IDA 2001, Proceedings",
}