Learning Semantic Features from Web Services

Abstract

In recent years the technological world has grown by incorporating billions of small sensing devices, collecting and sharing real-world information. As the number of such devices grows, it becomes increasingly difficult to manage all these new information sources. There is no uniform way to share, process and understand context information. It is our personal belief that IoT and M2M scenarios will only achieve their full potential when all the devices will work and learn together without human interaction. In this paper we review the most relevant semantic metrics and propose a new unsupervised model that minimizes sense-conflation problem. Our solution was evaluated against Miller-Charles dataset, outperforming our previous work in every metric.