From Semantic Vectors to Analogical Mapping

Human reasoning goes beyond knowledge about individual entities, extending to inferences based on relations between entities. Here we focus the use of in verbal analogical mapping, sketching a general approach assessing similarity patterns semantic words. This combines research artificial intelligence with work psychology and cognitive science, aim minimizing hand coding text inputs for tasks. The computational framework takes as vector representations word meanings, coupled words, uses these form semantic-relation networks analogues. Analogical mapping is operationalized graph matching under constraints. highlights central role semantics mapping.