Access the full text.
Sign up today, get DeepDyve free for 14 days.
Loading next page...
/lp/springer-journals/fast-and-accurate-text-classification-via-multiple-linear-discriminant-E3peRCnlgT
References (43)
-
T. Cooke (2002)
Two Variations on Fisher's Linear Discriminant for Pattern RecognitionIEEE Trans. Pattern Anal. Mach. Intell., 24
-
Glenn Fung, O. Mangasarian (2002)
Incremental Support Vector Machine Classification -
Yuh-Jye Lee, O. Mangasarian (2001)
RSVM: Reduced Support Vector Machines -
Also published as Data Mining Institute -
Hinrich Schütze, David Hull, Jan Pedersen (1995)
A comparison of classifiers and document representations for the routing problem -
P. Frankl, H. Maehara (1987)
The Johnson-Lindenstrauss lemma and the sphericity of some graphsJ. Comb. Theory, Ser. B, 44
-
D. Lewis (1997)
Reuters-21578 Text Categorization Test Collection, Distribution 1.0 -
O. Mangasarian, D. Musicant (2001)
Lagrangian Support Vector MachinesJ. Mach. Learn. Res., 1
-
T. Joachims (1998)
Text Categorization with Support Vector Machines: Learning with Many Relevant Features -
D. Lewis, R. Schapire, Jamie Callan, R. Papka (1996)
Training algorithms for linear text classifiers -
B. Scholkopf, C. Burges, Alex Smola (1999)
Advances in kernel methods: support vector learning -
Yann LeCun, P. Simard, Barak Pearlmutter (1992)
Automatic Learning Rate Maximization by On-Line Estimation of the Hessian's Eigenvectors, 5
-
R. Schapire (2003)
The Boosting Approach to Machine Learning An Overview -
A. Shashua (1999)
On the Relationship Between the Support Vector Machine for Classification and Sparsified Fisher's Linear DiscriminantNeural Processing Letters, 9
-
V. Vapnik, S. Golowich, Alex Smola (1996)
Support Vector Method for Function Approximation, Regression Estimation and Signal Processing -
C. Basu, H. Hirsh, William Cohen (1998)
Recommendation as Classification: Using Social and Content-Based Information in Recommendation -
J. Platt (1998)
Sequential Minimal Optimization : A Fast Algorithm for Training Support Vector MachinesMicrosoft Research Technical Report
-
T. Joachims (2001)
A statistical learning learning model of text classification for support vector machines -
A. Shashua, A. Shashua (1999)
On the Equivalence between the Support Vector Machine for Classiication and Sparsiied Fisher's Linear Discriminant -
Soumen Chakrabarti, B. Dom, R. Agrawal, P. Raghavan (1998)
Scalable feature selection, classification and signature generation for organizing large text databases into hierarchical topic taxonomiesThe VLDB Journal, 7
-
R. Agrawal, R. Bayardo, R. Srikant (2000)
Athena: Mining-Based Interactive Management of Text Database -
G. Graefe, U. Fayyad, S. Chaudhuri (1998)
On the Efficient Gathering of Sufficient Statistics for Classification from Large SQL Databases -
S. Dasgupta (1999)
Learning mixtures of Gaussians40th Annual Symposium on Foundations of Computer Science (Cat. No.99CB37039)
-
A. McCallum, K. Nigam (1998)
A comparison of event models for naive bayes text classification -
J. Kleinberg (1997)
Two algorithms for nearest-neighbor search in high dimensions -
T. Joachims (2001)
A Statistical Learning Model of Text Classification for Support Vector Machines. -
Sreerama Murthy, S. Kasif, S. Salzberg (1994)
A System for Induction of Oblique Decision TreesJ. Artif. Intell. Res., 2
-
(1998)
Bow: A toolkit for statistical language modeling, text retrieval, classification and clustering. Software available from http -
M. Sahami, S. Dumais, D. Heckerman, E. Horvitz (1998)
A Bayesian Approach to Filtering Junk E-Mail -
Yann LeCun, P. Simard, Barak Pearlmutter (1992)
Automatic Learning Rate Maximization in Large Adaptive Machines -
J. Shafer, R. Agrawal, Manish Mehta (1996)
SPRINT: A Scalable Parallel Classifier for Data Mining -
Glenn Fung, O. Mangasarian (2001)
Proximal support vector machine classifiers -
O. Mangasarian, D. Musicant (1999)
Successive overrelaxation for support vector machinesIEEE transactions on neural networks, 10 5
-
Dmitry Pavlov, J. Mao, B. Dom (2000)
Scaling-up support vector machines using boosting algorithmProceedings 15th International Conference on Pattern Recognition. ICPR-2000, 2
-
S. Dasgupta (2000)
Experiments with Random ProjectionArXiv, abs/1301.3849
-
T. Joachims (1998)
Making large scale SVM learning practicalTechnical reports
-
S. Dumais, John Platt, David Hecherman, M. Sahami (1992)
Ììì Öûûò Ë Blockinöö Óóóòòòö Áòøøöòòøøóòòð -
Richard Johnson, D. Wichern (1983)
Applied Multivariate Statistical Analysis -
(1999)
On the Equivalence Between the Support Vector Machine For Classification and . . . -
Deborah Swayne, D. Cook, A. Buja (1998)
XGobi: Interactive Dynamic Data Visualization in the X Window SystemJournal of Computational and Graphical Statistics, 7
-
R. Duda, P. Hart (1974)
Pattern classification and scene analysis -
S. Klinke, J. Polzehl (1995)
Exploratory Projection Pursuit -
K. Nigam, J. Lafferty, A. McCallum (1999)
Using Maximum Entropy for Text Classification
- Publisher
- Springer Journals
- Copyright
- Copyright © 2003 by Springer-Verlag
- Subject
- ComputerScience
- ISSN
- 1066-8888
- eISSN
- 0949-877X
- DOI
- 10.1007/s00778-003-0098-9
- Publisher site
- See Article on Publisher Site
Abstract
Support vector machines (SVMs) have shown superb performance for text classification tasks. They are accurate, robust, and quick to apply to test instances. Their only potential drawback is their training time and memory requirement. For n training instances held in memory, the best-known SVM implementations take time proportional to n a , where a is typically between 1.8 and 2.1. SVMs have been trained on data sets with several thousand instances, but Web directories today contain millions of instances that are valuable for mapping billions of Web pages into Yahoo!-like directories. We present SIMPL, a nearly linear-time classification algorithm that mimics the strengths of SVMs while avoiding the training bottleneck. It uses Fisher's linear discriminant, a classical tool from statistical pattern recognition, to project training instances to a carefully selected low-dimensional subspace before inducing a decision tree on the projected instances. SIMPL uses efficient sequential scans and sorts and is comparable in speed and memory scalability to widely used naive Bayes (NB) classifiers, but it beats NB accuracy decisively. It not only approaches and sometimes exceeds SVM accuracy, but also beats the running time of a popular SVM implementation by orders of magnitude. While describing SIMPL, we make a detailed experimental comparison of SVM-generated discriminants with Fisher's discriminants, and we also report on an analysis of the cache performance of a popular SVM implementation. Our analysis shows that SIMPL has the potential to be the method of choice for practitioners who want the accuracy of SVMs and the simplicity and speed of naive Bayes classifiers.
Journal
The VLDB Journal – Springer Journals
Published: Aug 1, 2003