Integrating Compound Terms in Bayesian Text Classification

Text classification usually assumed a word-based document representation. In this paper, we propose a new approach to integrate compound terms in Bayesian text classification. Compound terms are used as complementary features to single words. An acute problem is to consider their dependence with the...

Full description

Saved in:
Bibliographic Details
Published in:IEEE/WIC/ACM International Conference on web intelligence pp. 598 - 601
Main Authors: Bai, Jing, Nie, Jian-Yun, Cao, Guihong
Format: Conference Proceeding
Language:English
Published: Washington, DC, USA IEEE Computer Society 19.09.2005
IEEE
Series:ACM Conferences
Subjects:
Applied computing > Document management and text processing
Bayesian methods
Computing methodologies > Artificial intelligence > Natural language processing
Computing methodologies > Artificial intelligence > Natural language processing > Language resources
Computing methodologies > Machine learning > Learning paradigms > Supervised learning > Supervised learning by classification
Computing methodologies > Machine learning > Machine learning approaches > Classification and regression trees
Information retrieval
Mathematics of computing > Mathematical analysis > Numerical analysis > Interpolation
Niobium
Smoothing methods
Support vector machine classification
Support vector machines
Testing
Text categorization
Text recognition
Tree data structures
ISBN:076952415X, 9780769524153
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Text classification usually assumed a word-based document representation. In this paper, we propose a new approach to integrate compound terms in Bayesian text classification. Compound terms are used as complementary features to single words. An acute problem is to consider their dependence with the component words. In this paper, we propose to use smoothing techniques to combine both compound term and word representations. Experiments have been conducted on two corpora. Our results show that this approach can slightly but steadily improve the classification performance on both test corpora.
Bibliography:SourceType-Conference Papers & Proceedings-1
ObjectType-Conference Paper-1
content type line 25
ISBN:076952415X
9780769524153
DOI:10.1109/WI.2005.79