This paper presents a methodology for extending representation and reasoning in Qualitative Physics. This methodology is presently used for various applications. The qualitative modeling of a physical system is weakened by the lack of quantitative information. This may lead a qualitative analysis to ambiguity. One of the aims of this methodology is to cope with the lack of quantitative information. The main idea is to reproduce the physicist's ability to evaluate the influence of different phenomena according to their relative order of magnitude and to use this information to distinguish among radically different ways in which a physical system may behave. A formal system, FOG, is described in order to represent and structure this kind of apparentty vague and intuitive knowledge so that it can be used for qualitative reasoning.The validity of FOG for an interpretation in a mathematical theory called Non-Standard Analysis is then proven. Last, it is shown how FOG structures the quantity-space.
This paper presents a methodology for extending representation and reasoning in Qualitative Physics. This methodology is presently used for various applications. The qualitative modeling of a physical system is weakened by the lack of quantitative information. This may lead a qualitative analysis to ambiguity. One of the aims of this methodology is to cope with the lack of quantitative information. The main idea is to reproduce the physicist's ability to evaluate the influence of different phenomena according to their relative order of magnitude and to use this information to distinguish among radically different ways in which a physical system may behave. A formal system, FOG, is described in order to represent and structure this kind of apparentty vague and intuitive knowledge so that it can be used for qualitative reasoning.The validity of FOG for an interpretation in a mathematical theory called Non-Standard Analysis is then proven. Last, it is shown how FOG structures the quantity-space.
The wealth of structured (e.g. Wikidata) and unstructured data about the world available today presents an incredible opportunity for tomorrow's Artificial Intelligence. So far, integration of these two different modalities is a difficult process, involving many decisions concerning how best to represent the information so that it will be captured or useful, and hand-labeling large amounts of data. DeepType overcomes this challenge by explicitly integrating symbolic information into the reasoning process of a neural network with a type system. First we construct a type system, and second, we use it to constrain the outputs of a neural network to respect the symbolic structure. We achieve this by reformulating the design problem into a mixed integer problem: create a type system and subsequently train a neural network with it. In this reformulation discrete variables select which parent-child relations from an ontology are types within the type system, while continuous variables control a classifier fit to the type system. The original problem cannot be solved exactly, so we propose a 2-step algorithm: 1) heuristic search or stochastic optimization over discrete variables that define a type system informed by an Oracle and a Learnability heuristic, 2) gradient descent to fit classifier parameters. We apply DeepType to the problem of Entity Linking on three standard datasets (i.e. WikiDisamb30, CoNLL (YAGO), TAC KBP 2010) and find that it outperforms all existing solutions by a wide margin, including approaches that rely on a human-designed type system or recent deep learning-based entity embeddings, while explicitly using symbolic information lets it integrate new entities without retraining. 1 e.g. Do we overfit to a particular set of symbolic structures use-
The wealth of structured (e.g. Wikidata) and unstructured data about the world available today presents an incredible opportunity for tomorrow's Artificial Intelligence. So far, integration of these two different modalities is a difficult process, involving many decisions concerning how best to represent the information so that it will be captured or useful, and hand-labeling large amounts of data.DeepType overcomes this challenge by explicitly integrating symbolic information into the reasoning process of a neural network with a type system.First we construct a type system, and second, we use it to constrain the outputs of a neural network to respect the symbolic structure. We achieve this by reformulating the design problem into a mixed integer problem: create a type system and subsequently train a neural network with it. In this reformulation discrete variables select which parent-child relations from an ontology are types within the type system, while continuous variables control a classifier fit to the type system. The original problem cannot be solved exactly, so we propose a 2-step algorithm: 1) heuristic search or stochastic optimization over discrete variables that define a type system informed by an Oracle and a Learnability heuristic, 2) gradient descent to fit classifier parameters.We apply DeepType to the problem of Entity Linking on three standard datasets (i.e. WikiDisamb30, CoNLL (YAGO), TAC KBP 2010) and find that it outperforms all existing solutions by a wide margin, including approaches that rely on a human-designed type system or recent deep learning-based entity embeddings, while explicitly using symbolic information lets it integrate new entities without retraining.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.
customersupport@researchsolutions.com
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.