Text Categorization via Ellipsoid Separation

Andriy Kharechko; John Shawe-Taylor; Ralf Herbrich; Thore Graepel

Text Categorization via Ellipsoid Separation

Andriy Kharechko, John Shawe-Taylor, Ralf Herbrich, Thore Graepel

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

Abstract

We present a new batch learning algorithm for text classification in the vector space of document representations. The algorithm uses ellipsoid separation in the feature space which leads to a semidefinite program. An approximation of the latent semantic feature extraction approach using Gram-Schmidt orthogonalization is used for the feature extraction. Preliminary results demonstrate some potential for the presented approach.

Original language	Undefined
Title of host publication	Learning Methods for Text Understanding and Mining (26/01/04 - 29/01/04)
Publication status	Published (in print/issue) - 2004

Bibliographical note

Event Dates: 26 - 29 January 2004

Keywords

Text categorization
pattern separation
semidefinite programming
ellipsoid
latent semantic indexing
feature extraction
bag-of-words text representation
Gram-Schmidt orthogonalization.

Access to Document

https://eprints.soton.ac.uk/263412/

Cite this

@inproceedings{dd9e89e72fdf4d17bf931ad720c5d17d,

title = "Text Categorization via Ellipsoid Separation",

abstract = "We present a new batch learning algorithm for text classification in the vector space of document representations. The algorithm uses ellipsoid separation in the feature space which leads to a semidefinite program. An approximation of the latent semantic feature extraction approach using Gram-Schmidt orthogonalization is used for the feature extraction. Preliminary results demonstrate some potential for the presented approach.",

keywords = "Text categorization, pattern separation, semidefinite programming, ellipsoid, latent semantic indexing, feature extraction, bag-of-words text representation, Gram-Schmidt orthogonalization.",

author = "Andriy Kharechko and John Shawe-Taylor and Ralf Herbrich and Thore Graepel",

note = "Event Dates: 26 - 29 January 2004",

year = "2004",

language = "Undefined",

booktitle = "Learning Methods for Text Understanding and Mining (26/01/04 - 29/01/04)",

}

TY - GEN

T1 - Text Categorization via Ellipsoid Separation

AU - Kharechko, Andriy

AU - Shawe-Taylor, John

AU - Herbrich, Ralf

AU - Graepel, Thore

N1 - Event Dates: 26 - 29 January 2004

PY - 2004

Y1 - 2004

N2 - We present a new batch learning algorithm for text classification in the vector space of document representations. The algorithm uses ellipsoid separation in the feature space which leads to a semidefinite program. An approximation of the latent semantic feature extraction approach using Gram-Schmidt orthogonalization is used for the feature extraction. Preliminary results demonstrate some potential for the presented approach.

AB - We present a new batch learning algorithm for text classification in the vector space of document representations. The algorithm uses ellipsoid separation in the feature space which leads to a semidefinite program. An approximation of the latent semantic feature extraction approach using Gram-Schmidt orthogonalization is used for the feature extraction. Preliminary results demonstrate some potential for the presented approach.

KW - Text categorization

KW - pattern separation

KW - semidefinite programming

KW - ellipsoid

KW - latent semantic indexing

KW - feature extraction

KW - bag-of-words text representation

KW - Gram-Schmidt orthogonalization.

M3 - Conference contribution

BT - Learning Methods for Text Understanding and Mining (26/01/04 - 29/01/04)

ER -