skip to main content

This content will become publicly available on January 1, 2023

Title: Generative Inferences in Relational and Analogical Reasoning: A Comparison of Computational Models
A key property of human cognition is its ability to generate novel predictions about unfamiliar situations by completing a partially-specified relation or an analogy. Here, we present a computational model capable of producing generative inferences from relations and analogs. This model, BART-Gen, operates on explicit representations of relations learned by BART (Bayesian Analogy with Relational Transformations), to achieve two related forms of generative inference: reasoning from a single relation, and reasoning from an analog. In the first form, a reasoner completes a partially-specified instance of a stated relation (e.g., robin is a type of ____). In the second, a reasoner completes a target analog based on a stated source analog (e.g., sedan:car :: robin:____). We compare the performance of BART-Gen with that of BERT, a popular model for Natural Language Processing (NLP) that is trained on sentence completion tasks and that does not rely on explicit representations of relations. Across simulations and human experiments, we show that BART-Gen produces more human-like responses for generative inferences from relations and analogs than does the NLP model. These results demonstrate the essential role of explicit relation representations in human generative reasoning.
; ; ;
Award ID(s):
Publication Date:
Journal Name:
Proceedings of the 44th Annual Meeting of the Cognitive Science Society
Sponsoring Org:
National Science Foundation
More Like this
  1. Computational models of verbal analogy and relational similarity judgments can employ different types of vector representations of word meanings (embeddings) generated by machine-learning algorithms. An important question is whether human-like relational processing depends on explicit representations of relations (i.e., representations separable from those of the concepts being related), or whether implicit relation representations suffice. Earlier machine-learning models produced static embeddings for individual words, identical across all contexts. However, more recent Large Language Models (LLMs), which use transformer architectures applied to much larger training corpora, are able to produce contextualized embeddings that have the potential to capture implicit knowledge of semanticmore »relations. Here we compare multiple models based on different types of embeddings to human data concerning judgments of relational similarity and solutions of verbal analogy problems. For two datasets, a model that learns explicit representations of relations, Bayesian Analogy with Relational Transformations (BART), captured human performance more successfully than either a model using static embeddings (Word2vec) or models using contextualized embeddings created by LLMs (BERT, RoBERTa, and GPT-2). These findings support the proposal that human thinking depends on representations that separate relations from the concepts they relate.« less
  2. By middle childhood, humans are able to learn abstract semantic relations (e.g., antonym, synonym, category membership) and use them to reason by analogy. A deep theoretical challenge is to show how such abstract relations can arise from nonrelational inputs, thereby providing key elements of a protosymbolic representation system. We have developed a computational model that exploits the potential synergy between deep learning from “big data” (to create semantic features for individual words) and supervised learning from “small data” (to create representations of semantic relations between words). Given as inputs labeled pairs of lexical representations extracted by deep learning, the modelmore »creates augmented representations by remapping features according to the rank of differences between values for the two words in each pair. These augmented representations aid in coping with the feature alignment problem (e.g., matching those features that make “love-hate” an antonym with the different features that make “rich-poor” an antonym). The model extracts weight distributions that are used to estimate the probabilities that new word pairs instantiate each relation, capturing the pattern of human typicality judgments for a broad range of abstract semantic relations. A measure of relational similarity can be derived and used to solve simple verbal analogies with human-level accuracy. Because each acquired relation has a modular representation, basic symbolic operations are enabled (notably, the converse of any learned relation can be formed without additional training). Abstract semantic relations can be induced by bootstrapping from nonrelational inputs, thereby enabling relational generalization and analogical reasoning.

    « less
  3. Fitch, T. ; Lamm, C. ; Leder, H. ; Teßmar-Raible, K. (Ed.)
    Is analogical reasoning a task that must be learned to solve from scratch by applying deep learning models to massive numbers of reasoning problems? Or are analogies solved by computing similarities between structured representations of analogs? We address this question by comparing human performance on visual analogies created using images of familiar three-dimensional objects (cars and their subregions) with the performance of alternative computational models. Human reasoners achieved above-chance accuracy for all problem types, but made more errors in several conditions (e.g., when relevant subregions were occluded). We compared human performance to that of two recent deep learning models (Siamesemore »Network and Relation Network) directly trained to solve these analogy problems, as well as to that of a compositional model that assesses relational similarity between part-based representations. The compositional model based on part representations, but not the deep learning models, generated qualitative performance similar to that of human reasoners.« less
  4. Analogy problems involving multiple ordered relations of the same type create mapping ambiguity, requiring some mechanism for relational integration to achieve mapping accuracy. We address the question of whether the integration of ordered relations depends on their logical form alone, or on semantic representations that differ across relation types. We developed a triplet mapping task that provides a basic paradigm to investigate analogical reasoning with simple relational structures. Experimental results showed that mapping performance differed across orderings based on category, linear order, and causal relations, providing evidence that each transitive relation has its own semantic representation. Hence, human analogical mappingmore »of ordered relations does not depend solely on their formal property of transitivity. Instead, human ability to solve mapping problems by integrating relations relies on the semantics of relation representations. We also compared human performance to the performance of several vector-based computational models of analogy. These models performed above chance but fell short of human performance for some relations, highlighting the need for further model development.« less
  5. We see the external world as consisting not only of objects and their parts, but also of relations that hold between them. Visual analogy, which depends on similarities between relations, provides a clear example of how perception supports reasoning. Here we report an experiment in which we quantitatively measured the human ability to find analogical mappings between parts of different objects, where the objects to be compared were drawn either from the same category (e.g., images of two mammals, such as a dog and a horse), or from two dissimilar categories (e.g., a chair image mapped to a cat image).more »Humans showed systematic mapping patterns, but with greater variability in mapping responses when objects were drawn from dissimilar categories. We simulated the human response of analogical mapping using a computational model of mapping between 3D objects, visiPAM (visual Probabilistic Analogical Mapping). VisiPAM takes point-cloud representations of two 3D objects as inputs, and outputs the mapping between analogous parts of the two objects. VisiPAM consists of a visual module that constructs structural representations of individual objects, and a reasoning module that identifies a probabilistic mapping between parts of the two 3D objects. Model simulations not only capture the qualitative pattern of human mapping performance cross conditions, but also approach human-level reliability in solving visual analogy problems.« less