Emergence of analogy from relation learning
Open accessThe DOI matches its Crossref record; 41 of the 41 references it cites were found in a registry or an index.
Abstract
Significance: The ability to learn and make inferences based on relations is central to intelligence, underlying the distinctively human ability to reason by analogy across dissimilar situations. We have developed a computational model demonstrating that abstract relations, such as synonymy and antonymy, can be learned efficiently from semantic feature vectors for individual words and can be used to solve simple verbal analogy problems with close to human-level accuracy. The approach illustrates the potential synergy between deep learning from “big data” and supervised learning from “small data.” Core properties of high-level intelligence can emerge from relatively simple computations coupled with rich semantics. The model illustrates how operations on nonrelational inputs can give rise to protosymbolic relational representations.
Overview
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Integrity signals
Registry
Cites
Statistics
Figures




Verification
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Claims other papers make about this one
Each is checked against this paper’s own text: does it say what the citing paper says it does?
In the citing paper
“GPT3 also displayed strong zero-shot performance on letter string analogies, 16 four-term verbal analogies, 17,19-21 and identification of analogies between stories. 18,22,23”
From Emergent analogical reasoning in large language models (2023) · cites this paper as [19]
In the citing paper
“and on a dataset from Sternberg and Nigro 19 involving these same four relation types and linear order relations (Figure 7b).”
From Emergent analogical reasoning in large language models (2023) · cites this paper as [19]
In the citing paper
“The UCLA Verbal Analogy Test, 17 and the four-term verbal analogy sets from Sternberg and Nigro 19 and Jones et al. 21 are all available in a downloadable supplement in a recently published paper, 41 though to our knowledge they are not published directly in the form of webpages, and are thus unlikely to be included in web crawl data such as the Common Crawl dataset on which GPT-3 was trained.”
From Emergent analogical reasoning in large language models (2023) · cites this paper as [19]
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
Citations
Cites
Glove: Global Vectors for Word Representation
Pennington, J., Socher, R., & Manning, C. (2014) · Proceedings of the 2014 Conference on Empirical Methods in Natural Language Processing (EMNLP) · doi:10.3115/v1/d14-1162 · Cited by 34,071 · cited 2×
“Pennington J, Socher R, Manning CD (2014) GloVe: Global vectors for word representation.”
ResultDistributed Representations of Words and Phrases and their Compositionality
Mikolov, T., Sutskever, I., Chen, K., Corrado, G., & Dean, J. (2013) · arXiv · doi:10.48550/arxiv.1310.4546 · Cited by 24,533 · cited 11×
“In contrast to models that explicitly aim to learn relations, recent deep learning models, such as Word2vec (13, 14) and GloVe (15), have raised the possibility that basic relational reasoning can be achieved without explicit representations of relations.”
MethodResultInfluentialDistributed Representations of Sentences and Documents
Le, Q. V., & Mikolov, T. (2014) · arXiv (Cornell University) · doi:10.48550/arxiv.1405.4053 · Cited by 4,934 · cited 11×
“In contrast to models that explicitly aim to learn relations, recent deep learning models, such as Word2vec (13, 14) and GloVe (15), have raised the possibility that basic relational reasoning can be achieved without explicit representations of relations.”
MethodResultInfluentialCognitive representations of semantic categories.
Rosch, E. H. (1975) · Journal of Experimental Psychology General · doi:10.1037//0096-3445.104.3.192 · Cited by 4,756 · cited 2×
“Just as instances of basic object categories, such as fruit or furniture (24), follow a typicality ordering (e.”
BackgroundRepresentational similarity analysis-connecting the branches of systems neuroscience
Kriegeskorte, N. (2008) · Frontiers in Systems Neuroscience · doi:10.3389/neuro.06.004.2008 · Cited by 3,355
How to grow a mind: Statistics, structure, and abstraction
Tenenbaum, J. B., Kemp, C., Griffiths, T. L., & Goodman, N. D. (2011) · Science · doi:10.1126/science.1192788 · Cited by 1,815 · cited 1×
“One approach to addressing this issue has been to generate structural representations of relatively formal relations in a top-down manner by assuming an innate grammar of relations (8); however, such models have not addressed the acquisition of the lessclearly defined semantic relations that arise in natural languages.”
BackgroundThe structure-mapping engine: Algorithm and examples
Falkenhainer, B., Forbus, K. D., & Gentner, D. (1989) · Artificial Intelligence · doi:10.1016/0004-3702(89)90077-5 · Cited by 1,454
A simple neural network module for relational reasoning
Santoro, A., Raposo, D., Barrett, D. G. T., Malinowski, M., Pascanu, R., Battaglia, P., & Lillicrap, T. (2017) · arXiv · doi:10.48550/arxiv.1706.01427 · Cited by 1,281
Darwin's mistake: Explaining the discontinuity between human and nonhuman minds
Penn, D. C., Holyoak, K. J., & Povinelli, D. J. (2008) · Behavioral and Brain Sciences · doi:10.1017/s0140525x08003543 · Cited by 1,174 · cited 1×
“The capacity to reason using abstract relations is much more developed in humans than in any other species, perhaps constituting a qualitative difference in intelligence (1).”
Self-citationHalford, G. S., Wilson, W. H., & Phillips, S. (1998) · Behavioral and Brain Sciences · doi:10.1017/s0140525x98001769 · Cited by 912
Research works printed but not linked: 2
- AA Petrov Associative Memory-Based Reasoning: A Computational Model of Analogy-Making in a Decentralized Multi-Agent Cognitive Architecture (Lambert Academic, Saarbrücken, Germany, 2013).
- 10.1037/0096-3445.104.3.192 · doi:10.1037/0096-3445.104.3.192 · Paper page
Cited by
Emergent analogical reasoning in large language models
Webb, T., Holyoak, K. J., & Lu, H. (2023) · Nature Human Behaviour · doi:10.1038/s41562-023-01659-w · Cited by 404
Self-citationSemantic projection recovers rich human knowledge of multiple object features from word embeddings
Grand, G., Blank, I. A., Pereira, F., & Fedorenko, E. (2022) · Nature Human Behaviour · doi:10.1038/s41562-022-01316-8 · Cited by 187
Teaching by Analogy: From Theory to Practice
Gray, M. E., & Holyoak, K. J. (2021) · Mind Brain and Education · doi:10.1111/mbe.12288 · Cited by 138
Self-citationWord meaning in minds and machines.
Lake, B. M., & Murphy, G. L. (2023) · Psychological Review · doi:10.1037/rev0000297 · Cited by 131
Why concepts are (probably) vectors
Piantadosi, S. T., Muller, D. C. Y., Rule, J., Kaushik, K., Gorenstein, M. I., Leib, E. R., & Sanford, E. M. (2024) · Trends in Cognitive Sciences · doi:10.1016/j.tics.2024.06.011 · Cited by 87
Metadata
- Authors
- Lu, H., Wu, Y. N., & Holyoak, K. J.
- Affiliations
- University of California, Los Angeles (US)
- Corresponding author
- Lu, Hongjing
- Venue
- Proceedings of the National Academy of Sciences
- Publisher
- National Academy of Sciences
- Published
- 2019-02-15
- Volume
- 116
- Issue
- 10
- Pages
- 4176-4181
- ISSN
- 0027-8424 (ISSN-L)
- 1091-6490
- PMC
- PMC6410800
- OpenAlex
- W2913142708
- Cited by
- 70
- References
- 38
- Citations by year
- 2026: 1 · 2025: 9 · 2024: 7 · 2023: 12 · 2022: 10 · 2021: 10 · 2020: 14 · 2019: 7
- FWCI
- 4.68
- Type
- journal article
- Language
- en
- Open access
- hybrid
- doi.org
- Licence
- Locations
- Proceedings of the National Academy of Sciences (publishedVersion, cc-by-nc-nd)
- Europe PMC (PubMed Central) (publishedVersion, cc-by-nc-nd)
- PubMed Central (publishedVersion, cc-by-nc-nd)
- PubMed (publishedVersion)
- eScholarship (California Digital Library) (submittedVersion)
- Funders
- Google (Google Faculty Research Award)
- NSF | Directorate for Social, Behavioral and Economic Sciences (BCS-1827374)
- Topics
- Physical Sciences › Computer Science › Artificial Intelligence › Topic Modeling
- Social Sciences › Psychology › Experimental and Cognitive Psychology › Categorization, perception, and language
- Physical Sciences › Computer Science › Artificial Intelligence › Natural Language Processing Techniques
- Keywords
- analogy, relational learning, feature alignment, relational similarity, verbal analogies, antonymy, category membership, bootstrapping, computational model of language acquisition, middle childhood, typicality judgments
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
How to cite
Cite CoChat for the checks on this page, and the paper for its own findings.
- This page
- CoChat. (2026). Citation check: Emergence of analogy from relation learning. https://app.cochat.ai/papers/10.1073/pnas.1814779116
- The paper
- Lu, H., Wu, Y. N., & Holyoak, K. J. (2019). Emergence of analogy from relation learning. Proceedings of the National Academy of Sciences. https://doi.org/10.1073/pnas.1814779116
Data sources
Bibliographic data: Semantic Scholar, OpenAlex, Crossref.
Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).
Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.