Comprehending Meaning Through Number: The Transformation of Ideas from Ancient Doctrines to Artificial Intelligence Technologies

The article explores the evolution of the idea of correlating numbers and meanings, from ancient numerological systems to modern models of natural language processing based on vector representations and neural networks. The authors demonstrate that the aspiration to uncover hidden properties of objects by associating them with numbers and performing operations on these numbers has been a common thread across various cultures for millennia. The article traces the stages in the formation of the concept of mathesis universalis (universal mathematics), starting from Aristotle and Proclus’s reflections on general mathematics and culminating in R. Descartes’s ideas about the existence of a universally applicable science of order and measure. Particular attention is devoted to G.W. Leibniz’s ambitious project of creating a universal characteristic – a formalized language in which all knowledge could be precisely expressed and logical inference could be carried out through calculations. It is noted that, despite inherent limitations, some of Leibniz’s intuitions have found embodiment in natural language processing technologies based on vector representations of words. However, the simple correlation of concepts with vectors is insufficient for the full realization of the idea of a calculus of reasoning, as it lacks a mechanism for deriving true statements from others. The development of the transformer architecture, which employs the mechanism of self-attention to construct context-dependent vector representations, has been a significant stride towards the automation of reasoning. Nevertheless, modern language models are based on the principle of maximizing likelihood rather than rigorous logical rules. The authors analyze conceptual solutions proposed for creating a comprehensive calculus of knowledge. In conclusion, it is emphasized that, while the idea of reducing reasoning to mathematical operations is undeniably attractive, one should be cautious about its maximalist interpretations. Cognition is constructive in nature, and even the most perfect model of formalization of reasoning cannot substitute for the practical wisdom and freedom of human thought.

1. Aleksandrova N.V. (2008) History of Mathematical Terms, Concepts, and Notations: Dictionary-Reference. Moscow: LKI Publishing House (in Russian).

2. Aristotle (1976) Metaphysics. In: Aristotle. Collected Works (Vol. 1, pp. 65–367). Moscow: Mysl’ (Russian translation).

3. Asmus V.F. (1975) Plato. Moscow: Mysl’ (in Russian).

4. Bengio Y., Ducharme R., Vincent P., & Janvin C. (2003) A Neural Probabilistic Language Model. The Journal of Machine Learning Research. Vol. 3, pp. 1137–1155.

5. Bonner A. (2007) The Art and Logic of Ramon Llull. Leiden: Brill.

6. Brown T.B., Mann B., Ryder N., Subbiah M., Kaplan J., Dhariwal P., et al., & Amodei D. (2020) Language Models Are Few-Shot Learners. Advances in Neural Information Processing Systems. Vol. 33, pp. 1877–1901.

7. Clark P., Tafjord O., & Richardson K. (2020) Transformers as Soft Reasoners over Language. In: Bessiere C. (Ed.) Proceedings of the Twenty-Ninth International Joint Conference on Artificial Intelligence, IJCAI (pp. 3882–3890). Freiburg: IJCAI.

8. Descartes R. (1989) Rules for the Direction of the Mind (M.A. Garntsev, Trans.). In: Descartes R. Works (Vol. 1, pp. 77–153). Moscow: Mysl’ (Russian translation).

9. Frege G. (2000) Conceptual Notation: A Formula Language of Pure Thought, Modelled upon that of Arithmetic (B.V. Biryukov, Trans.). In: Frege G. Logic and Logical Semantics (pp. 65–142). Moscow: Aspekt Press (Russian translation).

10. Garcez A.D.A. & Lamb L.C. (2020) Neurosymbolic AI: The 3rd Wave. Artificial Intelligence Review. Vol. 56. No. 11, pp. 12387–12406.

11. Gregory A.D. (2015) The Pythagoreans: Number and Numerology. In: Lawrence S. & McCartney M. (Eds.) Mathematicians and their Gods (pp. 21–50). Oxford: Oxford University Press.

12. Guenon R. (1996) The Esoterism of Dante. Ghent: Sophia Perennis et Universalis.

13. Leibniz G.W. (1984a) On the Universal Science or Philosophical Calculus (G.G. Maiorov, Trans.). In: Leibniz G.W. Works (Vol. 3, pp. 494–500). Moscow: Mysl’ (Russian translation).

14. Leibniz G.W. (1984b) Elements of Universal Characteristics (N.A. Fedorov, Trans.). In: Leibniz G.W. Works (Vol. 3, pp. 506–513). Moscow: Mysl’ (Russian translation).

15. Leibniz G.W. (1984c) Elements of Calculus (N.A. Fedorov, Trans.). In: Leibniz G.W. Works (Vol. 3, pp. 514–522). Moscow: Mysl’ (Russian translation).

16. Leibniz G.W. (1984d) Elements of Universal Calculus (N.A. Fedorov, Trans.). In: Leibniz G.W. Works (Vol. 3, pp. 523–532). Moscow: Mysl’ (Russian translation).

17. Leibniz G.W. (1984e) Additions to the Experiment of Universal Calculus (G.G. Maiorov, Trans.). In: Leibniz G.W. Works (Vol. 3, pp. 564–571). Moscow: Mysl’ (Russian translation).

18. Leibniz G.W. (1989) Dissertation on the Art of Combinations, 1666 (Selections) (L.E. Loemker, Trans.). In: Leibniz G.W. Philosophical Papers and Letters: A Selection (2nd ed., pp. 73–84). Dordrecht: Kluwer.

19. Lundy M., Sutton D., Ashton A., & Martineau J. (2010) Quadrivium: The Four Classical Liberal Arts of Number, Geometry, Music, & Cosmology. New York: Bloomsbury.

20. Maas A.L., Daly R.E., Pham P.T., Huang D., Ng A.Y., & Potts C. (2011) Learning Word Vectors for Sentiment Analysis. In: Lin D., Matsumoto Y., & Mihalcea R. (Eds.) Proceedings of the 49th Annual Meeting of the Association for Computational Linguistics: Human Language Technologies (pp. 142–150). Portland, OR: Association for Computational Linguistics.

21. Mikolov T., Chen K., Corrado G., & Dean J. (2013) Efficient Estimation of Word Representations in Vector Space. arXiv preprint. arXiv:1301.3781.

22. Mill J.S. (2011) A System of Logic, Ratiocinative and Inductive: Being a Connected View of the Principles of Evidence and the Methods of Scientific Investigation (V.N. Ivanovsky, Trans.; V.K. Finn, Ed. & Intro.). Moscow: URSS (Russian translation).

23. Pennington J., Socher R., & Manning C.D. (2014) Glove: Global Vectors for Word Representation. In: Moschitti A., Pang B., & Daelemans W. (Eds.) Proceedings of the 2014 Conference on Empirical Methods in Natural Language Processing (EMNLP) (pp. 1532–1543). Stroudsburg, PA: Association for Computational Linguistics, 2014.

24. Proclus (1994) A Commentary on the First Book of Euclid’s Elements. Introduction (Yu.A. Shichalin, Trans.). Moscow: Greco-Latin Cabinet of Yu.A. Shichalin (Russian translation).

25. Proclus Diadochus (2013) A Commentary on the First Book of Euclid’s Elements (A.I. Shchetnikov, Trans.). Moscow: Russian Foundation for the Promotion of Education and Science (Russian translation).

26. Radford A., Narasimhan K., Salimans T., & Sutskever I. (2018) Improving Language Understanding by Generative Pre-Training. Retrieved from https://cdn.openai.com/research-covers/language-unsupervised/language_understanding_paper.pdf

27. Ruder S., Vulić I., & Søgaard A. (2019) A Survey of Cross-Lingual Word Embedding Models. Journal of Artificial Intelligence Research. Vol. 65, pp. 569–631.

28. Stewart M.D. (2001) The Amazing Significance of Numbers and Colors in the Sacred Scripture Texts (V.V. Monastyreva & M.V. Stetsenko, Trans.). Moscow: Vtoroye izdanie (Russian translation).

29. Turney P.D. & Pantel P. (2010) From Frequency to Meaning: Vector Space Models of Semantics. Journal of Artificial Intelligence Research. Vol. 37, pp. 141–188.

30. Vaswani A., Shazeer N., Parmar N., Uszkoreit J., Jones L., Gomez A.N., Kaiser Ł., & Polosukhin I. (2017) Attention Is All You Need. Advances in Neural Information Processing Systems. Vol. 30: NIPS 2017.

31. Voloshinov A.V. & Ryazanova N.V. (2011) Pythagorean Doctrine of Number: The Genesis of Number as an Object of Culture. Bulletin of the Saratov State Technical University. No. 1, pp. 336–342 (in Russian).

32. Wang X., Gao T., Zhu Z., Zhang Z., Liu Z., Li J., & Tang J. (2021) KEPLER: A Unified Model for Knowledge Embedding and Pre-Trained Language Representation. Transactions of the Association for Computational Linguistics. Vol. 9, pp. 176–194.

33. Weber J.-P. (1964) La constitution du texte des Regulæ. Paris: Société d’Édition d’Enseignement Supérieur.