Potential Uses in Breadth

  • Michael K. Bergman


This chapter overviews a dozen knowledge representation (KR) possibilities in breadth. Four potential near-term applications are word sense disambiguation, relation extraction, reciprocal mapping, and extreme knowledge supervision. Word sense disambiguation applied to new domains needs to overcome what is known as the knowledge acquisition bottleneck, which is the cost of finding, structuring, or annotating knowledge for WSD and other natural language processing applications. Relation extraction was also one of the first applications of the use of knowledge bases to inform labeled examples, what we now call distant supervision, which remains one of the better performing methods. All aspects of extracting, identifying, reconciling, and organizing the relation triple may be improved by KBpedia, which also should lead to new capabilities in ontology learning and better capabilities in question answering and data mining. We next cover four logics and representations in automatic hypothesis generation, encapsulating KBpedia for deep learning, measuring classifier performance, and the thermodynamics of representation itself. The last four areas include new applications and uses for knowledge graphs. Two of these, self-service business intelligence and semantic learning, have been on wish lists for years. The last two overviews apply Peirce’s ideas and guidance to nature and questions of the natural world. The examples in this chapter show the benefits of organizing our knowledge structures using Peirce’s universal categories and typologies. Further, with its graph structures and inherent connectedness, we also have some exciting graph learning methods that we can apply to KBpedia and its knowledge bases.


Applications Word sense disambiguation Information extraction Knowledge supervision 


  1. 1.
    Y. Xu, B.C. Malt, M. Srinivasan, Evolution of word meanings through metaphorical mapping: systematicity over the past millennium. Cogn. Psychol. 96, 41–53 (2017)CrossRefGoogle Scholar
  2. 2.
    C. Ramiro, B.C. Malt, M. Srinivasan, Y. Xu, Mental algorithms in the historical emergence of word meanings. Cogn. Sci., 986–991 (2017)Google Scholar
  3. 3.
    D. Oele, G. Van Noord, Distributional lesk: effective knowledge-based word sense disambiguation, in IWCS 2017—12th International Conference on Computational Semantics—Short papers (2017)Google Scholar
  4. 4.
    T. Mikolov, K. Chen, G. Corrado, J. Dean, Efficient estimation of word representations in vector space, arXiv:1301.3781 [cs] (2013)Google Scholar
  5. 5.
    D. Yarowsky, Unsupervised word sense disambiguation rivaling supervised methods. Association for Computational Linguistics, in Proceedings of the 33rd annual meeting on Association for Computational Linguistics (1995), pp. 189–196Google Scholar
  6. 6.
    P.S. Resnik, Selection and Information: A Class-Based Approach to Lexical Relationships. Ph.D., University of Pennsylvania (1993)Google Scholar
  7. 7.
    X. Sun, Structure regularization for structured prediction, in Advances in Neural Information Processing Systems (2014), pp. 2402–2410Google Scholar
  8. 8.
    M. Banko, E. Brill, Scaling to very large corpora for natural language disambiguation, association for computational linguistics, in Proceedings of the 39th Annual Meeting on Association for Computational Linguistics (2001), pp. 26–33Google Scholar
  9. 9.
    S.P. Ponzetto, R. Navigli, Knowledge-rich word sense disambiguation rivaling supervised systems. Association for Computational Linguistics, in Proceedings of the 48th Annual Meeting of the Association for Computational Linguistics (2010), pp. 1522–1531Google Scholar
  10. 10.
    E. Agirre, A. Barrena, A. Soroa, Studying the Wikipedia Hyperlink Graph for Relatedness and Disambiguation. arXiv:1503.01655 [cs] (2015)Google Scholar
  11. 11.
    M.A. Hearst, Automatic Acquisition of Hyponyms from Large Text Corpora, in Proceedings of the 14th Conference on Computational Linguistics-Volume 2. Association for Computational Linguistics (1992), pp. 539–545Google Scholar
  12. 12.
    M. Mintz, S. Bills, R. Snow, D. Jurafsky, Distant supervision for relation extraction without labeled data, in Proceedings of the 47th Annual Meeting of the ACL and the 4th IJCNLP of the AFNLP, vol. 2–7 (Suntec, 2009), pp. 1003–1011Google Scholar
  13. 13.
    D.B. Nguyen, M. Theobald, G. Weikum, J-REED: Joint Relation Extraction and Entity Disambiguation (ACM Press, Singapore, 2017), pp. 2227–2230Google Scholar
  14. 14.
    N. Bach, S. Badaskar, A review of relation extraction, in Literature Review for Language and Statistics II, vol. 2. (2007), pp. 1–15Google Scholar
  15. 15.
    H. Paulheim, Knowledge graph refinement: A survey of approaches and evaluation methods. Semantic Web 8, 489–508 (2017)CrossRefGoogle Scholar
  16. 16.
    B. Perozzi, R. Al-Rfou, S. Skiena, DeepWalk: Online learning of social representations, in Proceedings of the 20th ACM SIGKDD international conference on Knowledge discovery and data mining (2014), pp. 701–710Google Scholar
  17. 17.
    V. Ha-Thuc, J.-M. Renders, Large-Scale Hierarchical Text Classification Without Labelled Data (ACM Press, New York, NY, 2011), pp. 685–696Google Scholar
  18. 18.
    D. Traxl, N. Boers, J. Kurths, Deep graphs—a general framework to represent and analyze heterogeneous complex systems across scales. Chaos 26, 1–27 (2016)MathSciNetCrossRefGoogle Scholar
  19. 19.
    B.G. Johnston, M. Williams, in Conference on Artificial General Intelligence. A formal framework for the symbol grounding problem (Atlantis Press, Paris, 2009)Google Scholar
  20. 20.
    R. Neches, R.E. Fikes, T. Finin, T. Gruber, R. Patil, T. Senator, W.R. Swartout, Enabling technology for knowledge sharing. AI Magazine 12, 36 (1991)Google Scholar
  21. 21.
    Y. Song, D. Roth, Machine learning with world knowledge: the position and survey, arXiv:1705.02908 [cs, stat] (2017)Google Scholar
  22. 22.
    P. Cobreros, P. Égré, D. Ripley, R. van Rooij, Foreword: three-valued logics and their applications. J. Appl. Non-Classical Logics 24, 1–11 (2014)MathSciNetCrossRefGoogle Scholar
  23. 23.
    R. Lane, Triadic logic, in Digital Encyclopedia of Charles S. Peirce (2001)Google Scholar
  24. 24.
    C. Elsenbroich, O. Kutz, U. Sattler, A case for abductive reasoning over ontologies, in CEUR (2006), pp. 1–12Google Scholar
  25. 25.
    J. Du, K. Wang, Y.-D. Shen, A tractable approach to ABox abduction over description logic ontologies, in AAAI (2014), pp. 1034–1040Google Scholar
  26. 26.
    R.S. Prawat, Dewey, Peirce, and the learning paradox. Am. Educ. Res. J. 36, 47–76 (1999)CrossRefGoogle Scholar
  27. 27.
    P. Flach, A. Kakas, O. Ray, Abduction, induction, and the logic of scientific knowledge development, in Workshop on Abduction and Induction in AI and Scientific Modelling. (Citeseer, 2006), p. 21Google Scholar
  28. 28.
    P.A. Flach, in Abduction and Induction. On the logic of hypothesis generation (Springer, Dordrecht, 2000), pp. 89–106CrossRefGoogle Scholar
  29. 29.
    T. Kapitan, Peirce and the autonomy of Abductive reasoning. Erkenntnis 37, 1–26 (1992)MathSciNetCrossRefGoogle Scholar
  30. 30.
    T. Kapitan, In what way is Abductive inference creative? Trans. Charles S. Peirce Soc. 26, 499–512 (1990)Google Scholar
  31. 31.
    M. Tschaepe, Guessing and abduction. Trans. Charles S. Peirce Soc. 50, 115–138 (2014)CrossRefGoogle Scholar
  32. 32.
    G.E. Hinton, A. Krizhevsky, S.D. Wang, in International Conference on Artificial Neural Networks. Transforming auto-encoders (Springer, Berlin, Heidelberg, 2011), pp. 44–51Google Scholar
  33. 33.
    S. Sabour, N. Frosst, G.E. Hinton, Dynamic routing between capsules, in Advances in Neural Information Processing Systems (2017), pp. 3859–3869Google Scholar
  34. 34.
    F.J. Valverde-Albacete, C. Peláez-Moreno, 100% classification accuracy considered harmful: the normalized information transfer factor explains the accuracy paradox. PLoS One 9, 1–10 (2014)CrossRefGoogle Scholar
  35. 35.
    B. de Finetti, Foresight: its logical Laws, its subjective sources. Annales de l’Institut Henri Poincare 7, 94–158 (1937)Google Scholar
  36. 36.
    F.J. Valverde-Albacete, C. Peláez-Moreno, Two information-theoretic tools to assess the performance of multi-class classifiers. Pattern Recogn. Lett. 31, 1665–1671 (2010)CrossRefGoogle Scholar
  37. 37.
    S. Still, Thermodynamic Cost and Benefit of Data Representations. arXiv:1705.00612 [cond-­mat] (2017), pp. 1–8Google Scholar
  38. 38.
    S. Still, Information theoretic approach to interactive learning. EPL (Europhysics Letters) 85, 1–6 (2009)CrossRefGoogle Scholar
  39. 39.
    S. Still, D.A. Sivak, A.J. Bell, G.E. Crooks, Thermodynamics of prediction. Phys. Rev. Lett. 109, 1–5 (2012)CrossRefGoogle Scholar
  40. 40.
    S. Still, Information bottleneck approach to predictive inference. Entropy 16, 968–989 (Feb. 2014)CrossRefGoogle Scholar
  41. 41.
    TechTarget, in SearchBusinessAnalytics. What Is Self-Service Business Intelligence (BI)?
  42. 42.
    J. Stangarone, Self-Service Business Intelligence, mrc’s Cup of Joe Blog, 101 (2015)Google Scholar
  43. 43.
    A. Stutt, E. Motta, Semantic learning webs. J. Interact. Media Educ. 2004, 1–32 (2004)CrossRefGoogle Scholar
  44. 44.
    J. Sweller, S. Sweller, Natural information processing systems. Evol Psychol 4, 434–458 (2006). CrossRefGoogle Scholar
  45. 45.
    K. Wiesner, Nature computes: information processing in quantum dynamical systems. Chaos 20, 037114 (2010)MathSciNetCrossRefGoogle Scholar
  46. 46.
    N. Chomsky, Three models for the description of language. IRE Trans. Inf. Theory 2, 113–124 (1956)CrossRefGoogle Scholar
  47. 47.
    M. Burgin, G. Dodig-Crnkovic, Typologies of Computation and Computational Models. arXiv preprint arXiv:1312.2447 (2013), pp. 1–24Google Scholar
  48. 48.
    R. Quax, Information Processing in Complex Networks. Ph.D., University of Amsterdam (2013)Google Scholar
  49. 49.
    R. Quax, A. Apolloni, P.M.A. Sloot, Towards understanding the behavior of physical systems using information theory. Eur. Phys. J. Spec. Top. 222, 1389–1401 (2013)CrossRefGoogle Scholar
  50. 50.
    R. Quax, A. Apolloni, P.M.A. Sloot, The diminishing role of hubs in dynamical processes on complex networks. J. R. Soc. Interface 10, 1–10 (2013)CrossRefGoogle Scholar
  51. 51.
    G. Franzese, M. Visintin, Deep Information Networks. arXiv:1803.02251 [cs] (2018), pp. 1–10Google Scholar
  52. 52.
    A. Kleidon, R. Lorenz (eds.), Non-Equilibrium Thermodynamics and the Production of Entropy: Life, Earth, and Beyond (Springer, Berlin, New York, 2005)Google Scholar
  53. 53.
    R.E. Ulanowicz, S.J. Goerner, B. Lietaer, R. Gomez, Quantifying sustainability: resilience, efficiency and the return of information theory. Ecol. Complex. 6, 27–36 (2009)CrossRefGoogle Scholar
  54. 54.
    A. Kleidon, Non-equilibrium thermodynamics, maximum entropy production and Earth-­system evolution. Philos. Trans. A Math. Phys. Eng. Sci 368, 181–196 (2010)CrossRefGoogle Scholar
  55. 55.
    E. Zehe, T. Blume, G. Bloschl, The principle of ‘maximum energy dissipation’: a novel thermodynamic perspective on rapid water flow in connected soil structures. Philos Trans R Soc Lond B Biol Sci 365, 1377–1386 (2010)CrossRefGoogle Scholar
  56. 56.
    A. Kleidon, Life, hierarchy, and the thermodynamic machinery of planet earth. Phys Life Rev 7, 424–460 (2010)CrossRefGoogle Scholar
  57. 57.
    C. Herrmann-Pillath, Revisiting the Gaia Hypothesis: Maximum Entropy, Kauffman’s ‘Fourth Law’and Physiosemeiosis (Frankfurt School of Finance & Management, Frankfurt am Main, 2011)Google Scholar
  58. 58.
    S.A. Kauffman, Investigations (Oxford University Press, New York, 2000)Google Scholar

Copyright information

© Springer Nature Switzerland AG 2018

Authors and Affiliations

  • Michael K. Bergman
    • 1
  1. 1.Cognonto CorporationCoralvilleUSA

Personalised recommendations