A maximal figure-of-merit learning approach to text categorization

A novel maximal figure-of-merit (MFoM) learning approach to text categorization is proposed. Different from the conventional techniques, the proposed MFoM method attempts to integrate any performance metric of interest (e.g. accuracy, recall, precision, or F1 measure) into the design of any classifier. The corresponding classifier parameters are learned by optimizing an overall objective function of interest. To solve this highly nonlinear optimization problem, we use a generalized probabilistic descent algorithm. The MFoM learning framework is evaluated on the Reuters-21578 task with LSI-based feature extraction and a binary tree classifier. Experimental results indicate that the MFoM classifier gives improved F1 and enhanced robustness over the conventional one. It also outperforms the popular SVM method in

• Type: Conference
• Year: 2003
• Where: SIGIR
• Authors: Sheng Gao, Wen Wu, Chin-Hui Lee, Tat-Seng Chua
• Keywords: Binary Tree Classifier, Corresponding Classifier Parameters, Generalized Probabilistic Descent, SIGIR 2003