Sprinkling: supervised latent semantic indexing

Authors:
Sutanu Chakraborti;Robert Lothian;Nirmalie Wiratunga;Stuart Watt
Affiliations:
School of Computing, The Robert Gordon University, Aberdeen, Scotland, UK;School of Computing, The Robert Gordon University, Aberdeen, Scotland, UK;School of Computing, The Robert Gordon University, Aberdeen, Scotland, UK;School of Computing, The Robert Gordon University, Aberdeen, Scotland, UK
Venue:
ECIR'06 Proceedings of the 28th European conference on Advances in Information Retrieval
Year:
2006

Citing 5
Cited 6

Making large-scale support vector machine learning practical

Advances in kernel methods
Using LSI for text classification in the presence of background text

Proceedings of the tenth international conference on Information and knowledge management
Machine Learning

Machine Learning
A Memory-Based Approach to Anti-Spam Filtering for Mailing Lists

Information Retrieval
Using latent semantic indexing to filter spam

Proceedings of the 2003 ACM symposium on Applied computing

Supervised latent semantic indexing using adaptive sprinkling

IJCAI'07 Proceedings of the 20th international joint conference on Artifical intelligence
Introspective knowledge revision in textual case-based reasoning

ICCBR'10 Proceedings of the 18th international conference on Case-Based Reasoning Research and Development
Progress in information retrieval

ECIR'06 Proceedings of the 28th European conference on Advances in Information Retrieval
Selective integration of background knowledge in TCBR systems

ICCBR'11 Proceedings of the 19th international conference on Case-Based Reasoning Research and Development
Integration of Literature with Heterogeneous Information for Genes Correlation Scoring

ACM Journal on Emerging Technologies in Computing Systems (JETC) - Special Issue on Bioinformatics
Supervised word sense disambiguation using semantic diffusion kernel

Engineering Applications of Artificial Intelligence

Quantified Score

Hi-index	0.00

Visualization

Abstract

Latent Semantic Indexing (LSI) is an established dimensionality reduction technique for Information Retrieval applications. However, LSI generated dimensions are not optimal in a classification setting, since LSI fails to exploit class labels of training documents. We propose an approach that uses class information to influence LSI dimensions whereby class labels of training documents are endoded as new terms, which are appended to the documents. When LSI is carried out on the augmented term-document matrix, terms pertaining to the same class are pulled closer to each other. Evaluation over experimental data reveals significant improvement in classification accuracy over LSI. The results also compare favourably with naive Support Vector Machines.