Context modeling using a common sensedatabase

Abstract: Common sense databases are collections of human common sense knowledge. With these databases available, a lot of possibilities arise regarding understanding human language and putting it into a context. This essay aims to discuss how a common sense database could be used to enable a more human-like grasp of context in conversational agents. To try out the possibilities of context modeling using these databases we built a prototype that uses the knowledge base ConceptNet. Our tests showed that there are some issues with ConceptNet for our purposes regarding the quality of the data. However, we were still able to find some interesting previous research in the area, and were able to get some useful results using our prototype.