Memory Net: Generalizable Common-Sense Reasoning over Real-World Actions and Objects

Julian Eggert, Joerg Deigmoeller, Pavel Smirnov, Johane Takeuchi, Andreas Richter

2023

Abstract

In this paper, we explore how artificial agents (AAs) can understand and reason about so called ”action pat-terns” within real-world settings. Essentially, we want AAs to determine which tools fit specific actions, and which actions can be executed with certain tools, objects or agents, based on real-world situations. To achieve this, we utilize a comprehensive Knowledge Graph, called ”Memory Net” filled with interconnected everyday concepts, common actions, and environmental data. Our approach involves an inference technique that harnesses semantic proximity through subgraph matching. Comparing our approach against human responses and a state-of-the-art natural language model based machine learning approach in a home scenario, our Knowledge Graph method demonstrated strong generalization capabilities, suggesting its promise in dynamic, incremental and interactive real world settings.

Paper Citation

in Harvard Style

Eggert J., Deigmoeller J., Smirnov P., Takeuchi J. and Richter A. (2023). Memory Net: Generalizable Common-Sense Reasoning over Real-World Actions and Objects. In Proceedings of the 15th International Joint Conference on Knowledge Discovery, Knowledge Engineering and Knowledge Management - Volume 2: KEOD; ISBN 978-989-758-671-2, SciTePress, pages 182-189. DOI: 10.5220/0012182300003598

in Bibtex Style

@conference{keod23,
author={Julian Eggert and Joerg Deigmoeller and Pavel Smirnov and Johane Takeuchi and Andreas Richter},
title={Memory Net: Generalizable Common-Sense Reasoning over Real-World Actions and Objects},
booktitle={Proceedings of the 15th International Joint Conference on Knowledge Discovery, Knowledge Engineering and Knowledge Management - Volume 2: KEOD},
year={2023},
pages={182-189},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0012182300003598},
isbn={978-989-758-671-2},
}

in EndNote Style

TY - CONF

JO - Proceedings of the 15th International Joint Conference on Knowledge Discovery, Knowledge Engineering and Knowledge Management - Volume 2: KEOD
TI - Memory Net: Generalizable Common-Sense Reasoning over Real-World Actions and Objects
SN - 978-989-758-671-2
AU - Eggert J.
AU - Deigmoeller J.
AU - Smirnov P.
AU - Takeuchi J.
AU - Richter A.
PY - 2023
SP - 182
EP - 189
DO - 10.5220/0012182300003598
PB - SciTePress