Probabilistic Analogical Mapping with Semantic Relation Networks
This work addresses the challenge of enabling AI systems to perform flexible, domain-general analogical reasoning, which is incremental by building on existing semantic relation learning methods.
The authors tackled the problem of modeling human analogical reasoning by developing a Bayesian probabilistic graph matching model that operates on semantic relation networks derived from word embeddings. The model successfully accounts for a broad range of phenomena in analogical mapping tasks for both adults and children, as demonstrated through comparisons with human performance in novel and classic studies.
The human ability to flexibly reason using analogies with domain-general content depends on mechanisms for identifying relations between concepts, and for mapping concepts and their relations across analogs. Building on a recent model of how semantic relations can be learned from non-relational word embeddings, we present a new computational model of mapping between two analogs. The model adopts a Bayesian framework for probabilistic graph matching, operating on semantic relation networks constructed from distributed representations of individual concepts and of relations between concepts. Through comparisons of model predictions with human performance in a novel mapping task requiring integration of multiple relations, as well as in several classic studies, we demonstrate that the model accounts for a broad range of phenomena involving analogical mapping by both adults and children. We also show the potential for extending the model to deal with analog retrieval. Our approach demonstrates that human-like analogical mapping can emerge from comparison mechanisms applied to rich semantic representations of individual concepts and relations.