Domain Representation Using Possibility Theory: An Exploratory Study

Author

Khoury, Richard ; Karray, Fakhreddine ; Kamel, Mohamed S.

Author_Institution

Dept. of Electr. & Comput. Eng., Univ. of Waterloo, Waterloo, ON

Volume

16

Issue

6

fYear

2008

Firstpage

1531

Lastpage

1541

Abstract

This study explores a new domain representation method for natural language processing based on an application of possibility theory. In our method, domain-specific information is extracted from natural language documents using a mathematical process based on Rieger´s notion of semantic distances, and represented in the form of possibility distributions. We implement the distributions in the context of a possibilistic domain classifier, which is trained using the SchoolNet corpus.

Keywords

information retrieval; natural language processing; pattern classification; possibility theory; statistical distributions; text analysis; uncertainty handling; SchoolNet corpus; domain representation; domain-specific information; information extraction; mathematical process; natural language documents; natural language processing; possibilistic domain classifier; possibility distributions; possibility theory; semantic distances; “Fuzzy,” language models; natural language processing (NLP); probabilistic reasoning; text analysis; uncertainty;

fLanguage

English

Journal_Title

Fuzzy Systems, IEEE Transactions on

Publisher

ieee

ISSN

1063-6706

Type

jour

DOI

10.1109/TFUZZ.2008.2005011

Filename

4608719