Multi-Label Text Categorization with a Data Correlated VG-RAM Weightless Neural Network

In multi-label text categorization, one or more labels (or categories) can be assigned to a single document. In many such categorization tasks, there can be correlation on the assignment of subsets of the set of categories. This can be exploited to improve machine learning techniques devoted to multi-label text categorization. In this paper, we examine a Virtual Generalizing Random Access Memory Weightless Neural Network (VG-RAM WNN) architecture that takes advantage of the correlation between categories to improve text categorization performance. We compare the performance of this architecture, that we named Data Correlated VG-RAM WNN (VG-RAM WNN-COR), with that of standard VG-RAM WNN and ML-KNN categorizers using ten multi-label text categorization performance metrics. Our experimental results show that VG-RAM WNN-COR has an overall better performance than VG-RAM WNN and ML-KNN for the set of metrics considered.