Téléchargement | - Voir le manuscrit accepté : Semi-supervised Document Classification with a Mislabeling Error Model (PDF, 647 Kio)
|
---|
Auteur | Rechercher : Krithara, Anastasia; Rechercher : Amini, Massih R.; Rechercher : Renders, Jean-Michel; Rechercher : Goutte, Cyril1 |
---|
Affiliation | - Conseil national de recherches du Canada. Institut de technologie de l'information du CNRC
|
---|
Format | Texte, Article |
---|
Conférence | Advances in Information Retrieval, 30th European Conference on IR Research (ECIR'08), Glasgow, UK, March 30 - April 03, 2008 |
---|
Résumé | This paper investigates 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 ad- dition, 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 the effectiveness of our approach over two other semi-supervised algorithms applied to these text classification problems. |
---|
Date de publication | 2008 |
---|
Dans | |
---|
Langue | anglais |
---|
Publications évaluées par des pairs | Oui |
---|
Numéro du CNRC | NRCC 50728 |
---|
Numéro NPARC | 16435926 |
---|
Exporter la notice | Exporter en format RIS |
---|
Signaler une correction | Signaler une correction (s'ouvre dans un nouvel onglet) |
---|
Identificateur de l’enregistrement | 96fa3c52-f816-42de-8099-fd7df5fe6de5 |
---|
Enregistrement créé | 2010-11-25 |
---|
Enregistrement modifié | 2020-04-15 |
---|