University of Illinois Urbana-Champaign

Support Tensor Machines for Text Categorization

Cai, Deng; He, Xiaofei; Wen, Ji-Rong; Han, Jiawei; Ma, Wei-Ying

Content Files
Support Tensor Machines for Text Categorization.pdf

Permalink

https://hdl.handle.net/2142/11193

Description

Title
Support Tensor Machines for Text Categorization
Author(s)
  • Cai, Deng
  • He, Xiaofei
  • Wen, Ji-Rong
  • Han, Jiawei
  • Ma, Wei-Ying
Issue Date
2006-04
Keyword(s)
  • text categorization
  • text representation
  • computer science
Date of Ingest
2009-04-21T14:37:29Z
Abstract
We consider the problem of text representation and categorization. Conventionally, a text document is represented by a vector in high dimensional space. Some learning algorithms are then applied in such a vector space for text categorization. Particularly, Support Vector Machine (SVM) has received a lot of attentions due to its effectiveness. In this paper, we propose a new classification algorithm called {\bf Support Tensor Machine} (STM). STM uses {\bf Tensor Space Model} to represent documents. It considers a document as the second order tensor in \mathcal{R}^{n_1} \otimes \mathcal{R}^{n_2}$, where $\mathcal{R}^{n_1}$ and $\mathcal{R}^{n_2}$ are two vector spaces. With tensor representation, the number of parameters estimated by STM is much less than the number of parameters estimated by SVM. Therefore, our algorithm is especially suitable for small sample cases. We compared our proposed algorithm with SVM for text categorization on two standard databases. Experimental results show the effectiveness of our algorithm.
Type of Resource
text
Genre of Resource
Technical Report
Permalink
http://hdl.handle.net/2142/11193
Copyright and License Information
You are granted permission for the non-commercial reproduction, distribution, display, and performance of this technical report in any format, BUT this permission is only for a period of 45 (forty-five) days from the most recent time that you verified that this technical report is still available from the University of Illinois at Urbana-Champaign Computer Science Department under terms that include this permission. All other rights are reserved by the author(s).

Owning Collections

Research and Tech Reports - Computer Science PRIMARY