Plausible Reasoning Based on Qualitative Entity Embeddings
Proceedings of the Twenty-Fifth International Joint Conference on Artificial Intelligence. Pages 4078-4080.
Abstract
Formalizing and automating aspects of human plausible reasoning is an important challenge for the field of artificial intelligence. Practical advances, however, are hampered by the fact that most forms of plausible reasoning rely on background knowledge that is often not available in a structured form. In this paper, we first discuss how an important class of background knowledge can be induced from vector space representations that have been learned from (mostly) unstructured data. Subsequently, we advocate the use of qualitative abstractions of these vector spaces, as they are easier to obtain and manipulate, among others, while still supporting various forms of plausible reasoning.
@inproceedings{ijcai2016p605,
title = {Plausible Reasoning Based on Qualitative Entity Embeddings},
author = {Schockaert, Steven and Jameel, Shoaib},
booktitle = {Proceedings of the Twenty-Fifth International Joint Conference on
Artificial Intelligence, {IJCAI-16}},
publisher = {AAAI Press / International Joint Conferences on Artificial Intelligence},
editor = {Subbarao Kambhampati},
pages = {4078--4080},
year = {2016},
month = {7},
url = {https://ijcai.org/proceedings/2016/605},
}
TY - CPAPER TI - Plausible Reasoning Based on Qualitative Entity Embeddings AU - Schockaert, Steven AU - Jameel, Shoaib T2 - Proceedings of the Twenty-Fifth International Joint Conference on Artificial Intelligence, IJCAI-16 PB - AAAI Press / International Joint Conferences on Artificial Intelligence PY - 2016 SP - 4078 EP - 4080 UR - https://ijcai.org/proceedings/2016/605 ER -Copied
Machine-readable versions of this paper, for tools and AI agents:
