Voting experts: An unsupervised algorithm for segmenting sequences

Paul Cohen; Niall Adams; Brent Heeringa

doi:10.3233/ida-2007-11603

Voting experts: An unsupervised algorithm for segmenting sequences

Paul Cohen, Niall Adams, Brent Heeringa

Research output: Contribution to journal › Article › peer-review

50 Scopus citations

Abstract

We describe a statistical signature of chunks and an algorithm for finding chunks. While there is no formal definition of chunks, they may be reliably identified as configurations with low internal entropy or unpredictability and high entropy at their boundaries. We show that the log frequency of a chunk is a measure of its internal entropy. The Voting-Experts exploits the signature of chunks to find word boundaries in text from four languages and episode boundaries in the activities of a mobile robot.

Original language	English (US)
Pages (from-to)	607-625
Number of pages	19
Journal	Intelligent Data Analysis
Volume	11
Issue number	6
DOIs	https://doi.org/10.3233/ida-2007-11603
State	Published - 2007

ASJC Scopus subject areas

Theoretical Computer Science
Computer Vision and Pattern Recognition
Artificial Intelligence

Access to Document

10.3233/ida-2007-11603

Cite this

@article{19c8506e56c5423dacd9bd2c0a07d4d5,

title = "Voting experts: An unsupervised algorithm for segmenting sequences",

abstract = "We describe a statistical signature of chunks and an algorithm for finding chunks. While there is no formal definition of chunks, they may be reliably identified as configurations with low internal entropy or unpredictability and high entropy at their boundaries. We show that the log frequency of a chunk is a measure of its internal entropy. The Voting-Experts exploits the signature of chunks to find word boundaries in text from four languages and episode boundaries in the activities of a mobile robot.",

author = "Paul Cohen and Niall Adams and Brent Heeringa",

year = "2007",

doi = "10.3233/ida-2007-11603",

language = "English (US)",

volume = "11",

pages = "607--625",

journal = "Intelligent Data Analysis",

issn = "1088-467X",

publisher = "SAGE Publications Ltd",

number = "6",

}

TY - JOUR

T1 - Voting experts

T2 - An unsupervised algorithm for segmenting sequences

AU - Cohen, Paul

AU - Adams, Niall

AU - Heeringa, Brent

PY - 2007

Y1 - 2007

N2 - We describe a statistical signature of chunks and an algorithm for finding chunks. While there is no formal definition of chunks, they may be reliably identified as configurations with low internal entropy or unpredictability and high entropy at their boundaries. We show that the log frequency of a chunk is a measure of its internal entropy. The Voting-Experts exploits the signature of chunks to find word boundaries in text from four languages and episode boundaries in the activities of a mobile robot.

AB - We describe a statistical signature of chunks and an algorithm for finding chunks. While there is no formal definition of chunks, they may be reliably identified as configurations with low internal entropy or unpredictability and high entropy at their boundaries. We show that the log frequency of a chunk is a measure of its internal entropy. The Voting-Experts exploits the signature of chunks to find word boundaries in text from four languages and episode boundaries in the activities of a mobile robot.

UR - http://www.scopus.com/inward/record.url?scp=51449100133&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=51449100133&partnerID=8YFLogxK

U2 - 10.3233/ida-2007-11603

DO - 10.3233/ida-2007-11603

M3 - Article

AN - SCOPUS:51449100133

SN - 1088-467X

VL - 11

SP - 607

EP - 625

JO - Intelligent Data Analysis

JF - Intelligent Data Analysis

IS - 6

ER -

Voting experts: An unsupervised algorithm for segmenting sequences

Abstract

ASJC Scopus subject areas

Access to Document

Other files and links

Fingerprint

Cite this