Towards a Universal Text Classifier: Transfer Learning Using Encyclopedic Knowledge

Document classification is a key task for many text mining applications. However, traditional text classification requires labeled data to construct reliable and accurate classifiers. Unfortunately, labeled data are seldom available. In this work, we propose a {\textit {universal text classifier}}, which does not require any labeled document. Our approach simulates the capability of people to classify documents based on background knowledge. As such, we build a classifier that can effectively group documents based on their content, under the guidance of few words describing the classes of interest. Background knowledge is modeled using encyclopedic knowledge, namely Wikipedia. The universal text classifier can also be used to perform document retrieval. In our experiments with real data we test the feasibility of our approach for both the classification and retrieval tasks.