Papers
Topics
Authors
Recent
Gemini 2.5 Flash
Gemini 2.5 Flash
97 tokens/sec
GPT-4o
53 tokens/sec
Gemini 2.5 Pro Pro
44 tokens/sec
o3 Pro
5 tokens/sec
GPT-4.1 Pro
47 tokens/sec
DeepSeek R1 via Azure Pro
28 tokens/sec
2000 character limit reached

Analogical Proportions and Creativity: A Preliminary Study (2310.13500v1)

Published 20 Oct 2023 in cs.CL and cs.AI

Abstract: Analogical proportions are statements of the form "$a$ is to $b$ as $c$ is to $d$", which expresses that the comparisons of the elements in pair $(a, b)$ and in pair $(c, d)$ yield similar results. Analogical proportions are creative in the sense that given 3 distinct items, the representation of a 4th item $d$, distinct from the previous items, which forms an analogical proportion with them can be calculated, provided certain conditions are met. After providing an introduction to analogical proportions and their properties, the paper reports the results of an experiment made with a database of animal descriptions and their class, where we try to "create" new animals from existing ones, retrieving rare animals such as platypus. We perform a series of experiments using word embeddings as well as Boolean features in order to propose novel animals based on analogical proportions, showing that word embeddings obtain better results.

Definition Search Book Streamline Icon: https://streamlinehq.com
References (29)
  1. M. Boden. The Creative Mind: Myths and Mechanisms, 2nd edition. Routledge, 2004.
  2. M. Bounhas and H. Prade. Analogy-based classifiers: An improved algorithm exploiting competent data pairs. Int. J. Approx. Reason., 158:108923, 2023.
  3. Analogy-based classifiers for nominal or numerical data. Int. J. of Approximate Reasoning, 91:36 – 55, 2017.
  4. Comparison of analogy-based methods for predicting preferences. In N. Ben Amor, B. Quost, and M. Theobald, editors, Proc. 13th Int. Conf., on Scalable Uncertainty Management (SUM’19) Compiègne, Dec. 16-18, volume 11940 of LNCS, pages 339–354. Springer, 2019.
  5. S. Colton. Experiments in constraint-based automated scene generation. In P. Gervás, R. Pérez y Pérez, and T. Veale, editors, Proc. Int. Conf. on Computational Creativity, Madrid, pages 127–136, 2008.
  6. Constructive solving of Raven’s IQ tests with analogical proportions. Int. J. Intell. Syst., 31(11):1072–1103, 2016.
  7. BERT: Pre-training of deep bidirectional transformers for language understanding. In Proc. 2019 Conf. of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long and Short Papers), pages 4171–4186, Minneapolis, Minnesota, June 2019. Association for Computational Linguistics. doi: 10.18653/v1/N19-1423. URL https://aclanthology.org/N19-1423.
  8. T. G. Evans. A program for the solution of a class of geometric-analogy intelligence-test questions. In M. L. Minsky, editor, Semantic Information Processing, pages 271–353. MIT Press, Cambridge, Ma, 1968.
  9. M. A. Fahandar and E. Hüllermeier. Learning to rank based on analogical reasoning. In S. A. McIlraith and K. Q. Weinberger, editors, Proc. 32nd AAAI Conf. on Artificial Intelligence, (AAAI’18), New Orleans, Feb. 2-7, pages 2951–2958. AAAI Press, 2018.
  10. Analogy-based detection of morphological and semantic relations with word embeddings: what works and what doesn’t. In Proc. NAACL Student Research Workshop, pages 8–15, San Diego, California, June 2016. Association for Computational Linguistics. doi: 10.18653/v1/N16-2002. URL https://aclanthology.org/N16-2002.
  11. A. K. Goel. Design, analogy and creativity. IEEE Expert, 12:62–70, 1997.
  12. K. J. Holyoak and P. Thagard. Mental Leaps: Analogy in Creative Thought. MIT Press, 1995.
  13. In-context analogical reasoning with pre-trained language models. In Proc. 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 1953–1969, Toronto, Canada, July 2023. Association for Computational Linguistics. doi: 10.18653/v1/2023.acl-long.109. URL https://aclanthology.org/2023.acl-long.109.
  14. S. Klein. Culture, mysticism & social structure and the calculation of behavior. In Proc. 5th Europ. Conf. in Artificial Intelligence (ECAI’82), Orsay, France, pages 141–146, 1982.
  15. English WordNet 2019 – an open-source WordNet for English. In Proceedings of the 10th Global Wordnet Conference, pages 245–252, Wroclaw, Poland, July 2019. Global Wordnet Association. URL https://aclanthology.org/2019.gwc-1.31.
  16. L. Miclet and H. Prade. Handling analogical proportions in classical logic and fuzzy logics settings. In Proc. 10th Eur. Conf. on Symbolic and Quantitative Approaches to Reasoning with Uncertainty (ECSQARU’09),Verona, pages 638–650. Springer, LNCS 5590, 2009.
  17. Analogical dissimilarity: definition, algorithms and two experiments in machine learning. JAIR, 32, pages 793–824, 2008.
  18. Distributed representations of words and phrases and their compositionality. In C. J. C. Burges et al., editor, Advances in Neural Information Processing Systems 26, pages 3111–3119. Curran Associates Inc., 2013.
  19. GloVe: Global vectors for word representation. In Proc. 2014 Conf. on Empirical Methods in Natural Language Processing (EMNLP), pages 1532–1543, Doha, Qatar, October 2014. Assoc. for Comput. Ling. doi: 10.3115/v1/D14-1162.
  20. V. Pirrelli and F. Yvon. Analogy in the lexicon: a probe into analogy-based machine learning of language. In Proc. 6th Int. Symp. on Human Communic., 1999. Santiago de Cuba, 6 p.
  21. H. Prade and G. Richard. Analogical proportions: From equality to inequality. Int. J. of Approximate Reasoning, 101:234 – 254, 2018.
  22. H. Prade and G. Richard. Analogical proportions: Why they are useful in AI. In Proc. 30th Int. Joint Conf. on Artificial Intelligence (IJCAI-21), (Z.-H. Zhou, ed.) Virtual Event / Montreal, Aug. 19-27, pages 4568–4576, 2021a.
  23. H. Prade and G. Richard. Multiple analogical proportions. AI Commun., 34(3):211–228, 2021b.
  24. M. Ragni and S. Neubert. Analyzing raven’s intelligence test: Cognitive model, demand, and complexity. In Computational Approaches to Analogical Reasoning: Current Trends, volume 548 of Studies in Computational Intelligence, pages 351–370. Springer, 2014.
  25. A model for analogical reasoning. Cognitive Psychol., 5:1–28, 2005.
  26. J. Schmidhuber. Formal theory of creativity, fun, and intrinsic motivation (1990-2010). IEEE Trans. on Autonomous Mental Development, 2(3):230–247, 2010.
  27. T. Veale. An analogy-oriented type hierarchy for linguistic creativity. Knowledge-Based Systems, 19(7):471 – 479, 2006.
  28. Emergent analogical reasoning in large language models. Nature Human Behaviour, 7(9):1526–1541, 2023. ISSN 2397-3374. doi: 10.1038/s41562-023-01659-w. URL https://doi.org/10.1038/s41562-023-01659-w.
  29. ANALOGICAL - a novel benchmark for long text analogy evaluation in large language models. In Findings of the Association for Computational Linguistics: ACL 2023, pages 3534–3549, Toronto, Canada, July 2023. Association for Computational Linguistics. doi: 10.18653/v1/2023.findings-acl.218. URL https://aclanthology.org/2023.findings-acl.218.
User Edit Pencil Streamline Icon: https://streamlinehq.com
Authors (3)
  1. Stergos Afantenos (3 papers)
  2. Henri Prade (32 papers)
  3. Leonardo Cortez Bernardes (1 paper)

Summary

We haven't generated a summary for this paper yet.