Anastasia Krithara, Massih R. Amini, Jean-Michel Renders, Cyril Goutte
30th European Conference on Information Retrieval, ECIR, Glasgow, Scotland, 30 March-3 April 2008
This paper investigares a new extension of the Probabilistic Latent Semantic Analysis (PLSA) model [6] for text classification where the training set is partially labeled. The proposed approach iteratively labels the unlabeled documents and estimates the probabilities of its labeling errors. These probabilities are then taken into account in the estimation of the new model parameters before the next round. Our approach outperforms an earlier semi-supervised extension of PLSA introduced by [9] which is based on the use of fake labels. However it maintains its simplicity and ability to solve multiclass problems. In addition, it gives valuable information about the most uncertain and difficult classes to label. We perform experiments over the 20Newsgroups, WebKB and Reuters document collections and show effectiveness of our approach over two other semi-supervised algorithms applied to these text classification problems
Report number: