Transductive Inference for Text Classification using Support Vector Machines
T. Joachims.
Proceedings of ICML-99, 16th International Conference on Machine Learning, Seite 200--209. Bled, SL, Morgan Kaufmann Publishers, San Francisco, US, (1999)

This paper introduces Transductive Support Vector Machines (TSVMs) for text classifi cation. While regular Support Vector Ma chines (SVMs) try to induce a general deci sion function for a learning task, Transduc tive Support Vector Machines take into ac count a particular test set and try to mini mize misclassifications of just those particu lar examples. The paper presents an anal ysis of why TSVMs are well suited for text classification. These theoretical findings are supported by experiments on three test col lections. The experiments show substantial improvements over inductive methods, espe cially for small training sets, cutting the num ber of labeled training examples down to a twentieth on some tasks. This work also pro poses an algorithm for training TSVMs effi ciently, handling 10,000 examples and more.

Dokument

joachims99.ps

Suchen auf

Diese Publikation wurde noch nicht bewertet.

Bewertungsverteilung

Durchschnittliche Benutzerbewertung0,0 von 5.0 auf Grundlage von 0 Rezensionen

Bitte melden Sie sich an um selbst Rezensionen oder Kommentare zu erstellen.

@inproceedings{joachims1999transductive,
  abstract = {This paper introduces Transductive Support Vector Machines (TSVMs) for text classifi cation. While regular Support Vector Ma chines (SVMs) try to induce a general deci sion function for a learning task, Transduc tive Support Vector Machines take into ac count a particular test set and try to mini mize misclassifications of just those particu lar examples. The paper presents an anal ysis of why TSVMs are well suited for text classification. These theoretical findings are supported by experiments on three test col lections. The experiments show substantial improvements over inductive methods, espe cially for small training sets, cutting the num ber of labeled training examples down to a twentieth on some tasks. This work also pro poses an algorithm for training TSVMs effi ciently, handling 10,000 examples and more.},
  added-at = {2011-02-04T16:09:51.000+0100},
  address = {Bled, SL},
  author = {Joachims, Thorsten},
  biburl = {https://puma.uni-kassel.de/bibtex/27cf3e7981cac898c1745418db83e0fd6/benz},
  booktitle = {Proceedings of {ICML}-99, 16th International Conference on Machine Learning},
  editor = {Bratko, Ivan and Dzeroski, Saso},
  file = {joachims1999transductive.pdf:joachims1999transductive.pdf:PDF},
  interhash = {7b7737625402ab3e8db5f53d1de716d6},
  intrahash = {7cf3e7981cac898c1745418db83e0fd6},
  keywords = {studienarbeit eventually_useful},
  lastdatemodified = {2005-08-06},
  lastname = {Joachims},
  own = {own},
  pages = {200--209},
  pdf = {joachims99.pdf},
  publisher = {Morgan Kaufmann Publishers, San Francisco, US},
  read = {notread},
  timestamp = {2011-02-04T16:09:51.000+0100},
  title = {Transductive Inference for Text Classification using Support Vector Machines},
  url = {joachims99.ps},
  year = 1999
}

%0 Conference Paper
%1 joachims1999transductive
%A Joachims, Thorsten
%B Proceedings of ICML-99, 16th International Conference on Machine Learning
%C Bled, SL
%D 1999
%E Bratko, Ivan
%E Dzeroski, Saso
%I Morgan Kaufmann Publishers, San Francisco, US
%K studienarbeit eventually_useful
%P 200--209
%T Transductive Inference for Text Classification using Support Vector Machines
%U joachims99.ps
%X This paper introduces Transductive Support Vector Machines (TSVMs) for text classifi cation. While regular Support Vector Ma chines (SVMs) try to induce a general deci sion function for a learning task, Transduc tive Support Vector Machines take into ac count a particular test set and try to mini mize misclassifications of just those particu lar examples. The paper presents an anal ysis of why TSVMs are well suited for text classification. These theoretical findings are supported by experiments on three test col lections. The experiments show substantial improvements over inductive methods, espe cially for small training sets, cutting the num ber of labeled training examples down to a twentieth on some tasks. This work also pro poses an algorithm for training TSVMs effi ciently, handling 10,000 examples and more.

PUMA

Transductive Inference for Text Classification using Support Vector Machines
T. Joachims.
Proceedings of ICML-99, 16th International Conference on Machine Learning, Seite 200--209. Bled, SL, Morgan Kaufmann Publishers, San Francisco, US, (1999)

Tags

Nutzer

Kommentare und Rezensionen

Zitieren Sie diese Publikation

PUMA

Transductive Inference for Text Classification using Support Vector MachinesT. Joachims. Proceedings of ICML-99, 16th International Conference on Machine Learning, Seite 200--209. Bled, SL, Morgan Kaufmann Publishers, San Francisco, US, (1999)

Tags

Nutzer

Kommentare und Rezensionen

Zitieren Sie diese Publikation

Transductive Inference for Text Classification using Support Vector Machines
T. Joachims.
Proceedings of ICML-99, 16th International Conference on Machine Learning, Seite 200--209. Bled, SL, Morgan Kaufmann Publishers, San Francisco, US, (1999)