Learning Aspect Models with Partially Labeled Data

Printer-friendly versionSend by email
Α. Krithara, M. Amini, C. Goutte and J.M. Renders
In this paper, we address the problem of learning aspectmodels with partially labeled data for the task of document categorization. The motivation of this work is to take advantage of the amount of available unlabeled data together with the set of labeled examples to learn latent models whose structure and underlying hypotheses take more accurately into account the document generation process, compared to other mixture-based generative models. We present one semi-supervised variant of the Probabilistic Latent Semantic Analysis (PLSA) model (Hofmann, 2001). In our approach, we try to capture the possible data mislabeling errors which occur during the training of our model. This is done by iteratively assigning class labels to unlabeled examples using the current aspectmodel and re-estimating the probabilities of the mislabeling errors. We perform experiments over the 20Newsgroups, WebKB and Reuters document collections, as well as over a real world dataset coming from a Business Group of Xerox and show the effectiveness of our approach compared to a semi-supervised version of Naive Bayes, another semi-supervised version of PLSA and to transductive Support Vector Machines.
Software and Knowledge Engineering Laboratory (SKEL)
Content Analysis and Knowledge Technologies (CAKT)
Publication Name: 
Pattern Recognition Letters
Page Start: 
Page End: 

© 2018 - Institute of Informatics and Telecommunications | National Centre for Scientific Research "Demokritos"