A “stereo” document representation for textual information retrieval

Authors:
Liang Chen;Jia Zeng;Naoyuki Tokuda
Affiliations:
Computer Science Department, University of Northern British Columbia, 3333 University Way, Prince George, BC, Canada V2N 4Z9;Computer Science Department, University of Northern British Columbia, 3333 University Way, Prince George, BC, Canada V2N 4Z9;SunFlare R & D Center, Shinjuku Hirose Bldg, Yotsuya 4-7, Shinjuku-ku, Tokyo, Japan 160-0004
Venue:
Journal of the American Society for Information Science and Technology
Year:
2006

Citing 6
Cited 3

Face recognition with one training image per person

Pattern Recognition Letters
Combining document representations for known-item search

Proceedings of the 26th annual international ACM SIGIR conference on Research and development in informaion retrieval
Metasearch: data fusion for document retrieval

Metasearch: data fusion for document retrieval
A new differential LSI space-based probabilistic document classifier

Information Processing Letters
The SMART Retrieval System—Experiments in Automatic Document Processing

The SMART Retrieval System—Experiments in Automatic Document Processing
AutoTutor: A simulation of a human tutor

Cognitive Systems Research

Supporting polyrepresentation in a quantum-inspired geometrical retrieval framework

Proceedings of the third symposium on Information interaction in context
What can quantum theory bring to information retrieval

CIKM '10 Proceedings of the 19th ACM international conference on Information and knowledge management
Exploring a multidimensional representation of documents and queries

RIAO '10 Adaptivity, Personalization and Fusion of Heterogeneous Information

Quantified Score

Hi-index	0.00

Visualization

Abstract

A new document representation model is presented in this paper. This model is based on the idea of representing a document by two or more pictures of the document taken from different perspectives. It is shown that by applying the stereo representation model, enhanced textual retrieval performance is achieved because the new model improves the capability of capturing individual features of the document. Experiments have been conducted on two standard corpora, TIME and ADI, using the standard term vector method and the latent semantic indexing (LSI) method based upon both the stereo representation model and the traditional representation model. Statistical t-tests on the experimental results have convincingly illustrated that these methods achieve significant improvements in retrieval performances with the stereo representation model over those with the traditional representation model. © 2006 Wiley Periodicals, Inc.