Learned latent vector representations are key to the success of many recommender systems in recent years. However, traditional approaches like matrix factorization, produce vector representations that capture global distributions of a static recommendation scenario only. Such latent user or item representations, do not capture background knowledge and are not customized to a concrete situational context and the sequential history of events leading up to it.
Infusing autonomous artificial systems with knowledge about the physical world they inhabit is of utmost importance and a long lasting goal in Artificial Intelligence (AI) research. Training systems with relevant data is a common approach; yet, it is not always feasible to find the data needed, especially since a big portion of this knowledge is commonsense. In this paper, we propose a novel method for extracting and evaluating relations about objects and actions from web knowledge graphs, such as ConceptNet and WordNet.
The H2020 InterConnect project aims to improve the semantic interoperability in the smart home, building and grid domain. The project has a budget of 35 million euro’s and gathers 50 European entities from 11 countries. An vital component for success is its interoperability layer, which allows platforms, services and devices (knowledge bases) from different vendors to exchange data. The interoperability layer was designed to utilize semantic technologies like ontologies and reasoning. InterConnect’s interoperability layer will be realized by the Knowledge Engine.