Advertisement

Compositionality and Contextuality: The Symbolic and Statistical Theories of Meaning

  • Yoshihiro MaruyamaEmail author
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 11939)

Abstract

Compositionality and contextuality give two fundamental principles of linguistic analysis, and yet there is a conflict between them as Burge, Dummett, and others find. Here we aim at elucidating conceptual views underlying their tension in light of both symbolic and statistical paradigms of semantics, arguing, inter alia, that: (i) the conflict is a case of vicious circle analogous to hermeneutic circularity, and may be understood as a tension between symbolic and statistical semantics; (ii) the productivity, systematicity, and learnability of language can be accounted for in accordance with the principle of contextuality as well as compositionality; and (iii) the Chomsky versus Norvig debate on the (symbolic versus statistical) nature of language may be considered a broader manifestation of the tension in the form of the traditional conflict in philosophy between rationalist and empiricist worldviews. We conclude the paper with an outlook for the Kantian synthesis of them, especially the categorical integration of symbolic and statistical AI.

References

  1. 1.
    Baroni, M., et al.: Frege in space: a program of compositional distributional semantics. Linguist. Issues Lang. Technol. 9, 5–110 (2014)Google Scholar
  2. 2.
    Bourguignat, C.: Interpretable VS Powerful Predictive Models: Why We Need Them Both, Medium, 17 September 2014. Accessed on 16 July 2019Google Scholar
  3. 3.
    Burge, T.: Truth, Thought, Reason: Essays on Frege. Clarendon, Oxford (2005)CrossRefGoogle Scholar
  4. 4.
    Chomsky, N.: Syntactic Structures. Mouton & Co, Berlin (1957)zbMATHGoogle Scholar
  5. 5.
    Chomsky, N.: Recent contributions to the theory of innate ideas. In: Stitch, S. (ed.) Innate Ideas. California University Press, Berkeley (1975)zbMATHGoogle Scholar
  6. 6.
    Chomsky, N., Ronat, M.: Language and Responsibility: Based on Conversations with Mitsou Ronat. Pantheon Books, Paris (1979)Google Scholar
  7. 7.
    Chomsky, N.: Keynote Panel: The Golden Age - A Look at the Original Roots of Artificial Intelligence, Cognitive Science, and Neuroscience, MIT Symposium on Brains, Minds, and Machines. Accessed on 23 June 2019Google Scholar
  8. 8.
    Coecke, B., et al.: Mathematical foundations for a compositional distributional model of meaning. Linguist. Anal. 36, 345–384 (2010)Google Scholar
  9. 9.
    Davidson, D.: Truth and Meaning. Synthese 17, 304–323 (1967)CrossRefGoogle Scholar
  10. 10.
    Domingos, P., et al.: Unifying logical and statistical AI. In: Proceedings of the 31st Annual ACM/IEEE Symposium on Logic in Computer Science, pp. 1–11 (2016)Google Scholar
  11. 11.
    Dummett, M.: The Interpretation of Frege’s Philosophy. Duckworth, London (1981)Google Scholar
  12. 12.
    Evans, J.: The History and Practice of Ancient Astronomy. Oxford University Press, Oxford (1998)Google Scholar
  13. 13.
    Frege, G.: The Foundations of Arithmetic. Basil Blackwell, Oxford (1953). (originally 1884)zbMATHGoogle Scholar
  14. 14.
    Frege, G.: Compound thoughts. Mind 72, 1–17 (1963). (originally 1923)CrossRefGoogle Scholar
  15. 15.
    Frege, G.: The Philosophical and Mathematical Correspondence. University of Chicago Press, Chicago (1980)zbMATHGoogle Scholar
  16. 16.
    Gold, K.: Norvig vs. Chomsky and the Fight for the Future of AI, TOR.COM, 21 June 2011. Accessed on 26 June 2019Google Scholar
  17. 17.
    Janssen, T.: Frege, contextuality and compositionality. J. Logic Lang. Inf. 10, 87–114 (2001)MathSciNetCrossRefGoogle Scholar
  18. 18.
    Katz, Y.: Noam Chomsky on Where Artificial Intelligence Went Wrong, The Atlantic, 1 November 2012. Accessed on 23 June 2019Google Scholar
  19. 19.
    Kuhn, M., Johnson, K.: Applied Predictive Modeling. Springer, New York (2013).  https://doi.org/10.1007/978-1-4614-6849-3CrossRefzbMATHGoogle Scholar
  20. 20.
    Landauer, T.: On the computational basis of learning and cognition: arguments from LSA. Psychol. Learn. Motiv. 41, 43–84 (2002)CrossRefGoogle Scholar
  21. 21.
    Markie, P.: Rationalism vs. Empiricism, Stanford Encyclopedia of Philosophy (2017)Google Scholar
  22. 22.
    Maxwell, J.C.: The Scientific Letters and Papers of James Clerk Maxwell: 1846–1862. Cambridge University Press, Cambridge (1990)zbMATHGoogle Scholar
  23. 23.
    Norvig, P.: On chomsky and the two cultures of statistical learning. Berechenbarkeit der Welt?, pp. 61–83. Springer, Wiesbaden (2017).  https://doi.org/10.1007/978-3-658-12153-2_3CrossRefGoogle Scholar
  24. 24.
    Pelletier, F.J.: The principle of semantic compositionality. Topoi 13, 11–24 (1994)MathSciNetCrossRefGoogle Scholar
  25. 25.
    Pelletier, F.J.: Did frege believe frege’s principle? J. Logic Lang. Inf. 10, 87–114 (2001)MathSciNetCrossRefGoogle Scholar
  26. 26.
    Szabó, Z.G.: Compositionality, Stanford Encyclopedia of Philosophy (2017)Google Scholar
  27. 27.
    Turney, P., Pantel, P.: From frequency to meaning: vector space models of semantics. J. Artif. Intell. Res. 37, 141–188 (2010)MathSciNetCrossRefGoogle Scholar
  28. 28.
    Wittgenstein, L.: Tractatus Logico-Philosophicus. Humanities Press, New York (1961). (originally 1922)zbMATHGoogle Scholar
  29. 29.
    Wittgenstein, L.: Zettel. University of California Press, California (1967)zbMATHGoogle Scholar

Copyright information

© Springer Nature Switzerland AG 2019

Authors and Affiliations

  1. 1.The Hakubi Centre for Advanced ResearchKyoto UniversityKyotoJapan

Personalised recommendations