11th Joint International Conference on Information Sciences

Type-2 Fuzzy Classifier Ensembles for Text Entailment

Authors
Asli Celikyilmaz 0, I. Burhan Turksen
Corresponding Author
Asli Celikyilmaz
0University of California, Berkeley
Available Online December 2008.
DOI
https://doi.org/10.2991/jcis.2008.11How to use a DOI?
Keywords
type-2 fuzzy sets, classifier ensembles, fuzzy c-classification.
Abstract
This paper presents a new Type-2 Fuzzy Classifier ensemble, which enables to model parameter uncertainties by charac-terizing the fuzzy sets with secondary membership values. We use fuzzy clus-tering method to characterize primary membership values and genetic algorithm to approximate secondary membership grades. Furthermore, a weighing algo-rithm is used for a non-complex reduction for reasoning. We use transductive rea-soning, instead of inductive reasoning, to develop a local model for every new vec-tor, based on a nearness criterion vectors from the given database. It is shown that the method can improve classifier system modeling performance in comparison to well-known methods.
Open Access
This is an open access article distributed under the CC BY-NC license.

Download article (PDF)

Proceedings
11th Joint International Conference on Information Sciences
Part of series
Advances in Intelligent Systems Research
Publication Date
December 2008
ISBN
978-90-78677-18-5
ISSN
1951-6851
DOI
https://doi.org/10.2991/jcis.2008.11How to use a DOI?
Open Access
This is an open access article distributed under the CC BY-NC license.

Cite this article

TY  - CONF
AU  - Asli Celikyilmaz
AU  - I. Burhan Turksen
PY  - 2008/12
DA  - 2008/12
TI  - Type-2 Fuzzy Classifier Ensembles for Text Entailment
BT  - 11th Joint International Conference on Information Sciences
PB  - Atlantis Press
SN  - 1951-6851
UR  - https://doi.org/10.2991/jcis.2008.11
DO  - https://doi.org/10.2991/jcis.2008.11
ID  - Celikyilmaz2008/12
ER  -