@inproceedings{68481e4d727e43fbbcaf09682f54de9e,
title = "Removing statistical biases in unsupervised sequence learning",
abstract = "Unsupervised sequence learning is important to many applications. A learner is presented with unlabeled sequential data, and must discover sequential patterns that characterize the data. Popular approaches to such learning include statistical analysis and frequency based methods. We empirically compare these approaches and find that both approaches suffer from biases toward shorter sequences, and from inability to group together multiple instances of the same pattern. We provide methods to address these deficiencies, and evaluate them extensively on several synthetic and real-world data sets. The results show significant improvements in all learning methods used.",
author = "Yoav Horman and Kaminka, {Gal A.}",
year = "2005",
doi = "10.1007/11552253_15",
language = "אנגלית",
isbn = "3540287957",
series = "Lecture Notes in Computer Science (including subseries Lecture Notes in Artificial Intelligence and Lecture Notes in Bioinformatics)",
publisher = "Springer Verlag",
pages = "157--167",
booktitle = "Advances in Intelligent Data Analysis VI - 6th International Symposium on Intelligent Data Analysis, IDA 2005, Proceedings",
address = "גרמניה",
note = "6th International Symposium on Intelligent Data Analysis, IDA 2005 ; Conference date: 08-09-2005 Through 10-09-2005",
}