Training algorithms for linear text classifiers
David D. Lewis, Robert E. Schapire, James P. Callan et al. · International ACM SIGIR Conference on Research and Development in Information Retrieval (SIGIR) · 1996
Systems for text retrieval, routing, categorization and other IR tasks rely heavily on linear classifiers.We propose that two machine learning algorithms, the Widrow-Hoff and EG algorithms, be used in training linear text classifiers.In contrast to most IR methods, theoretical analysis provides performance guarantees and guidance on parameter settings for these algorithms.Experimental data is presented showing Widrow-Hoff and EG to be more effective than the widely used Rocchio algorithm on several categorization and routing tasks.
Cited by 520 works. doi:10.1145/243199.243277 Open-access PDF
Authors
References
- Nonparametric Statistics for the Behavioral Sciences
- Pattern classification and scene analysis
- Introduction to Modern Information Retrieval
- Term-weighting approaches in automatic text retrieval
- Pattern classification and scene analysis
- Nonparametric Statistics for the Behavioral Sciences.
- Adaptive Signal Processing
- Introduction to modern information retrieval
- Relevance weighting of search terms
- Relevance feedback in information retrieval