Deductive and Analogical Reasoning on a Semantically Embedded Knowledge Graph
نویسنده
چکیده
Representing knowledge as high-dimensional vectors in a continuous semantic vector space can help overcome the brittleness and incompleteness of traditional knowledge bases. We present a method for performing deductive reasoning directly in such a vector space, combining analogy, association, and deduction in a straightforward way at each step in a chain of reasoning, drawing on knowledge from diverse sources and ontologies.
منابع مشابه
Integrating Natural Language, Knowledge Representation and Reasoning, and Analogical Processing to Learn by Reading
•radically change the economics of building large knowledge bases •provide a platform for cognitive simulations of larger-scale phenomena •Learning Reader learns by reading simplified language texts •Manages syntactic complexity •Unconstrained vocabulary, unlike controlled languages •Learning Reader combines •Natural language processing •A large-scale knowledge base •Deductive reasoning •Analog...
متن کامل‘Soft’ Approaches to Analogical Alignment and Sub-Graph Isomorphism
Structure-mapping is a process of isomorphic sub-graph alignment that is exploited in metaphor, analogy and exemplar-based reasoning. Once a mapping between two knowledge structures from different domains is created in this way, knowledge from one domain (the well-understood source) can be transferred to the other (the lessunderstood target). However, in many cases both domains might be semanti...
متن کاملConnecting long distance: semantic distance in analogical reasoning modulates frontopolar cortex activity.
Solving problems often requires seeing new connections between concepts or events that seemed unrelated at first. Innovative solutions of this kind depend on analogical reasoning, a relational reasoning process that involves mapping similarities between concepts. Brain-based evidence has implicated the frontal pole of the brain as important for analogical mapping. Separately, cognitive research...
متن کاملIntegrity Constraint and Rule Maintenance in Temporal Deductive Knowledge Bases
The enforcement of semantic integrity constraints in data and knowledge bases constitutea a major performance bottleneck. Integrity constraint simplification methods aim at reducing the complexity of formula evaluation at run-time. This paper proposes such a simplification method for large and semantically rich knowledge bases. Structural, temporal and assertional knowledge in the form of deduc...
متن کاملInterpretation of Design Drawings by Analogy
Visual analogical mapping and transfer can be used to derive a structural model of a drawing by analogy, and, moreover, the problem of analogical mapping can be guided by using functional knowledge. We view the interpretation drawings of designs as deriving a structural model of the components and connections of the depicted device. This problem is not deductive in nature but, rather, it is abd...
متن کامل