Using focus of attention in classification

Y. Even-Zohar

doi:10.1109/SCCC.2000.890398

Using focus of attention in classification

Y. Even-Zohar

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

Abstract

The goal of a classifier is to accurately predict the value of a class given its context. Often the number of classes "competing" for each prediction is large. Therefore, it is necessary to "focus attention" on a smaller subset of these. We investigate the contribution of a "focus of attention" mechanism using enablers to the performance of a word predictor. We then describe a large scale experimental study in which the approach presented is shown to yield significant improvements in word prediction tasks.

Original language	English
Title of host publication	Proceedings - 20th International Conference of the Chilean Computer Science Society, SCCC 2000
Publisher	IEEE Computer Society
Pages	109-116
Number of pages	8
ISBN (Electronic)	0769508103
DOIs	https://doi.org/10.1109/SCCC.2000.890398
State	Published - 2000
Externally published	Yes
Event	20th International Conference of the Chilean Computer Science Society, SCCC 2000 - Santiago, Chile Duration: 16 Nov 2000 → 18 Nov 2000

Publication series

Name	Proceedings - International Conference of the Chilean Computer Science Society, SCCC
Volume	2000-January
ISSN (Print)	1522-4902

Conference

Conference	20th International Conference of the Chilean Computer Science Society, SCCC 2000
Country/Territory	Chile
City	Santiago
Period	16/11/00 → 18/11/00

Bibliographical note

Publisher Copyright:
© 2000 IEEE.

Keywords

Artificial intelligence
Computer science
Large-scale systems
Merging
Probability distribution
Speech recognition
Testing

ASJC Scopus subject areas

General Engineering
General Computer Science

Access to Document

10.1109/SCCC.2000.890398

Cite this

@inproceedings{2173c89a049343f5b209c34f8392c80e,

title = "Using focus of attention in classification",

abstract = "The goal of a classifier is to accurately predict the value of a class given its context. Often the number of classes {"}competing{"} for each prediction is large. Therefore, it is necessary to {"}focus attention{"} on a smaller subset of these. We investigate the contribution of a {"}focus of attention{"} mechanism using enablers to the performance of a word predictor. We then describe a large scale experimental study in which the approach presented is shown to yield significant improvements in word prediction tasks.",

keywords = "Artificial intelligence, Computer science, Large-scale systems, Merging, Probability distribution, Speech recognition, Testing",

author = "Y. Even-Zohar",

note = "Publisher Copyright: {\textcopyright} 2000 IEEE.; 20th International Conference of the Chilean Computer Science Society, SCCC 2000 ; Conference date: 16-11-2000 Through 18-11-2000",

year = "2000",

doi = "10.1109/SCCC.2000.890398",

language = "English",

series = "Proceedings - International Conference of the Chilean Computer Science Society, SCCC",

publisher = "IEEE Computer Society",

pages = "109--116",

booktitle = "Proceedings - 20th International Conference of the Chilean Computer Science Society, SCCC 2000",

address = "United States",

}

Even-Zohar, Y 2000, Using focus of attention in classification. in Proceedings - 20th International Conference of the Chilean Computer Science Society, SCCC 2000., 890398, Proceedings - International Conference of the Chilean Computer Science Society, SCCC, vol. 2000-January, IEEE Computer Society, pp. 109-116, 20th International Conference of the Chilean Computer Science Society, SCCC 2000, Santiago, Chile, 16/11/00. https://doi.org/10.1109/SCCC.2000.890398

Using focus of attention in classification. / Even-Zohar, Y.
Proceedings - 20th International Conference of the Chilean Computer Science Society, SCCC 2000. IEEE Computer Society, 2000. p. 109-116 890398 (Proceedings - International Conference of the Chilean Computer Science Society, SCCC; Vol. 2000-January).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

TY - GEN

T1 - Using focus of attention in classification

AU - Even-Zohar, Y.

PY - 2000

Y1 - 2000

N2 - The goal of a classifier is to accurately predict the value of a class given its context. Often the number of classes "competing" for each prediction is large. Therefore, it is necessary to "focus attention" on a smaller subset of these. We investigate the contribution of a "focus of attention" mechanism using enablers to the performance of a word predictor. We then describe a large scale experimental study in which the approach presented is shown to yield significant improvements in word prediction tasks.

AB - The goal of a classifier is to accurately predict the value of a class given its context. Often the number of classes "competing" for each prediction is large. Therefore, it is necessary to "focus attention" on a smaller subset of these. We investigate the contribution of a "focus of attention" mechanism using enablers to the performance of a word predictor. We then describe a large scale experimental study in which the approach presented is shown to yield significant improvements in word prediction tasks.

KW - Artificial intelligence

KW - Computer science

KW - Large-scale systems

KW - Merging

KW - Probability distribution

KW - Speech recognition

KW - Testing

UR - https://www.scopus.com/pages/publications/84883108902

U2 - 10.1109/SCCC.2000.890398

DO - 10.1109/SCCC.2000.890398

M3 - Conference contribution

AN - SCOPUS:84883108902

T3 - Proceedings - International Conference of the Chilean Computer Science Society, SCCC

SP - 109

EP - 116

BT - Proceedings - 20th International Conference of the Chilean Computer Science Society, SCCC 2000

PB - IEEE Computer Society

T2 - 20th International Conference of the Chilean Computer Science Society, SCCC 2000

Y2 - 16 November 2000 through 18 November 2000

ER -

Using focus of attention in classification

Abstract

Publication series

Conference

Bibliographical note

Keywords

ASJC Scopus subject areas

Access to Document

Other files and links

Fingerprint

Cite this