High-quality Training Data Selection using Latent Topics for Graph-based Semi-supervised Learning
Akiko Eriguchi, Ichiro Kobayashi · 2013
In a multi-class document categorization using graph-based semi-supervised learning (GBSSL), it is essential to construct a proper graph expressing the relation among nodes and to use a reasonable categorization algorithm. Furthermore, it is also important to provide high-quality correct data as training data. In this context, we propose a method to construct a similarity graph by employing both surface information and latent information to express similarity between nodes and a method to select high-quality training data for GBSSL by means of the PageRank algorithm. Experimenting on Reuters-21578 corpus, we have confirmed that our proposed methods work well for raising the accuracy of a multi-class document categorization. 1