Discriminative Methods for Multi-Labeled Classification
S. Godbole, и S. Sarawagi. In Proceedings of the 8th Pacific-Asia Conference on Knowledge Discovery and Data Mining, стр. 22--30. Springer, (2004)
Аннотация
In this paper we present methods of enhancing existing discriminative classifiers for multi-labeled predictions. Discriminative methods like support vector machines perform very well for uni-labeled text classification tasks. Multi-labeled classification is a harder task subject to relatively less attention. In the multi-labeled setting, classes are often related to each other or part of a is-a hierarchy. We present a new technique for combining text features and features indicating relationships between classes, which can be used with any discriminative algorithm.
Описание
CiteSeerX — Discriminative Methods for Multi-Labeled Classification
%0 Conference Paper
%1 Godbole04discriminativemethods
%A Godbole, Shantanu
%A Sarawagi, Sunita
%B In Proceedings of the 8th Pacific-Asia Conference on Knowledge Discovery and Data Mining
%D 2004
%I Springer
%K ml multi-label use_y
%P 22--30
%T Discriminative Methods for Multi-Labeled Classification
%U http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.1.3819
%X In this paper we present methods of enhancing existing discriminative classifiers for multi-labeled predictions. Discriminative methods like support vector machines perform very well for uni-labeled text classification tasks. Multi-labeled classification is a harder task subject to relatively less attention. In the multi-labeled setting, classes are often related to each other or part of a is-a hierarchy. We present a new technique for combining text features and features indicating relationships between classes, which can be used with any discriminative algorithm.
@inproceedings{Godbole04discriminativemethods,
abstract = {In this paper we present methods of enhancing existing discriminative classifiers for multi-labeled predictions. Discriminative methods like support vector machines perform very well for uni-labeled text classification tasks. Multi-labeled classification is a harder task subject to relatively less attention. In the multi-labeled setting, classes are often related to each other or part of a is-a hierarchy. We present a new technique for combining text features and features indicating relationships between classes, which can be used with any discriminative algorithm.},
added-at = {2011-03-30T16:27:58.000+0200},
author = {Godbole, Shantanu and Sarawagi, Sunita},
biburl = {https://www.bibsonomy.org/bibtex/2f1296d042f24f2f01e8c075a7b97ccbf/jrquevedogmail},
booktitle = {In Proceedings of the 8th Pacific-Asia Conference on Knowledge Discovery and Data Mining},
description = {CiteSeerX — Discriminative Methods for Multi-Labeled Classification},
interhash = {7624432f6d327450b3f2e2e65c85e8c1},
intrahash = {f1296d042f24f2f01e8c075a7b97ccbf},
keywords = {ml multi-label use_y},
pages = {22--30},
publisher = {Springer},
timestamp = {2011-04-06T10:04:31.000+0200},
title = {Discriminative Methods for Multi-Labeled Classification},
url = {http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.1.3819},
year = 2004
}