Rank Prediction for Semantically Annotated Resources

In the context of semantic knowledge bases, we tackle the problem of ranking resources w.r.t. some criterion. The pro- posed solution is a method for learning functions that can approximately predict the correct ranking. Differently from other related methods proposed, that assume the ranking criteria to be explicitly expressed (e.g. as a query or a func- tion), our approach is data-driven, being able to produce a predictor detecting the implicit underlying criteria from as- sertions regarding the resources in the knowledge base. The usage of specific kernel functions encoding the similarity be- tween individuals in the context of knowledge bases allows the application of the method to ontologies in the standard representations for the Semantic Web. The method is based on a kernelized version of the Perceptron Ranking algo- rithm which is suitable for batch but also online problem settings. Moreover, differently from other approaches based on regression, the method takes advantage from the under- lying ordering on the ranking labels. The reported empirical evaluation proves the effectiveness of the method at the task of predicting the rankings of single users in the Linked User Feedback dataset, by integrating knowledge from the Linked Open Data cloud during the learning process.