Dimensions of Commonsense Knowledge
Authors
Ilievski, Filip
Oltramari, Alessandro
Ma, Kaixin
Zhang, Bin
McGuinness, Deborah L.
Szekely, Pedro
ORCID
No Thumbnail Available
Other Contributors
Issue Date
2021-10-11
Keywords
Machine Common Sense (MCS) Multi-modal Open World Grounded Learning and Inference (MOWGLI)
Degree
Terms of Use
Full Citation
Abstract
Commonsense knowledge is essential for many AI applications, including those in natural language processing, visual processing, and planning. Consequently, many sources that include commonsense knowledge have been designed and constructed over the past decades. Recently, the focus has been on large text-based sources, which facilitate easier integration with neural (language) models and application to textual tasks, typically at the expense of the semantics of the sources and their harmonization. Efforts to consolidate commonsense knowledge have yielded partial success, with no clear path towards a comprehensive solution. We aim to organize these sources around a common set of dimensions of commonsense knowledge. We survey a wide range of popular commonsense sources with a special focus on their relations. We consolidate these relations into 13 knowledge dimensions. This consolidation allows us to unify the separate sources and to compute indications of their coverage, overlap, and gaps with respect to the knowledge dimensions. Moreover, we analyze the impact of each dimension on downstream reasoning tasks that require commonsense knowledge, observing that the temporal and desire/goal dimensions are very beneficial for reasoning on current downstream tasks, while distinctness and lexical knowledge have little impact. These results reveal preferences for some dimensions in current evaluation, and potential neglect of others.
Description
Department
Publisher
Knowledge-Based Systems
Relationships
https://tw.rpi.edu/project/machine-common-sense-mcs-multi-modal-open-world-grounded-learning-and-inference-mowgli