Object-Action Association Extraction from Knowledge Graphs

Research & Innovation

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. We present a complete methodology of locating, enriching, evaluating, cleaning and exposing knowledge from such resources, taking into consideration semantic similarity methods. We compare our method with typical approaches found in the relevant literature, such as methods which exploit the topology or the semantic information in a knowledge graph, and embeddings. We test the performance of these methods on the Something Something Dataset.

Speakers: 

Available material for this talk.
Recording