A Vector Field Approach to Lexical Semantics

  • Peter Wittek
  • Sándor DarányiEmail author
  • Ying-Hsang Liu
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 8951)


We report work in progress on measuring “forces” underlying the semantic drift by comparing it with plate tectonics in geology. Based on a brief survey of energy as a key concept in machine learning, and the Aristotelian concept of potentiality vs. actuality allowing for the study of energy and dynamics in language, we propose a field approach to lexical analysis. Until evidence to the contrary, it was assumed that a classical field in physics is appropriate to model word semantics. The approach used the distributional hypothesis to statistically model word meaning. We do not address the modelling of sentence meaning here. The computability of a vector field for the indexing vocabulary of the Reuters-21578 test collection by an emergent self-organizing map suggests that energy minima as learnables in machine learning presuppose concepts as energy minima in cognition. Our finding needs to be confirmed by a systematic evaluation.


Weight Vector Word Meaning Concept Drift Test Collection Sentence Meaning 
These keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.



The authors are grateful for the comments of three anonymous reviewers. Numerous suggestions from the audience of QI-14 helped to link our work to ongoing parallel research in the field. The current development phase of Somoclu was supported by the European Commission Seventh Framework Programme under Grant Agreement Number FP7-601138 PERICLES.


  1. 1.
    Antoniou, G., d’Aquin, M., Pan, J.Z.: Semantic web dynamics. Web Seman. Sci. Serv. Agents World Wide Web 9, 245–246 (2011)CrossRefGoogle Scholar
  2. 2.
    Lauriston, A.: Criteria for measuring term recognition. In: Proceedings of EACL-95, 7th Conference of the European Chapter of the Association for Computational Linguistics, pp. 17–22 (1995)Google Scholar
  3. 3.
    Gulla, J.A., Solskinnsbakk, G., Myrseth, P., Haderlein, V., Cerrato, O.: Concept signatures and semantic drift. In: Filipe, J., Cordeiro, J. (eds.) WEBIST 2010. LNBIP, vol. 75, pp. 101–113. Springer, Berlin (2011)CrossRefGoogle Scholar
  4. 4.
    Delany, S.J., Cunningham, P., Tsymbal, A., Coyle, L.: A case-based technique for tracking concept drift in spam filtering. Knowl. Based Syst. 18, 187–195 (2005)CrossRefGoogle Scholar
  5. 5.
    Wang, S., Schlobach, S., Klein, M.: Concept drift and how to identify it. Web Seman. Sci. Serv. Agents World Wide Web 9, 247–265 (2011)CrossRefGoogle Scholar
  6. 6.
    Ross, G.J., Adams, N.M., Tasoulis, D.K., Hand, D.J.: Exponentially weighted moving average charts for detecting concept drift. Pattern Recogn. Lett. 33, 191–198 (2012)CrossRefGoogle Scholar
  7. 7.
    Gonçalves Jr., P.M., Barros, R.S.M.: Rcd: A recurring concept drift framework. Pattern Recogn. Lett. 34, 1018–1025 (2013)CrossRefGoogle Scholar
  8. 8.
    Turney, P.D., Pantel, P.: From frequency to meaning: vector space models of semantics. J. Artif. Intell. Res. 37, 141–188 (2010)zbMATHMathSciNetGoogle Scholar
  9. 9.
    Padó, S., Lapata, M.: Dependency-based construction of semantic space models. Comput. Linguist. 33, 161–199 (2007)CrossRefzbMATHGoogle Scholar
  10. 10.
    Erk, K., Padó, S.: A structured vector space model for word meaning in context. In: Proceedings of EMNLP-08, 13th Conference on Empirical Methods in Natural Language Processing, pp. 897–906. (2008)Google Scholar
  11. 11.
    Socher, R., Huval, B., Manning, C.D., Ng, A.Y.: Semantic compositionality through recursive matrix-vector spaces. In: Proceedings of EMNLP-CoNLL-12, Joint Conference on Empirical Methods in Natural Language Processing and Computational Natural Language Learning, pp. 1201–1211 (2012)Google Scholar
  12. 12.
    Baroni, M., Lenci, A.: Distributional memory: a general framework for corpus-based semantics. Comput. Linguist. 36, 673–721 (2010)CrossRefGoogle Scholar
  13. 13.
    Blacoe, W., Kashefi, E., Lapata, M.: A quantum-theoretic approach to distributional semantics. In: Proceedings of NAACL-HLT-13, Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, pp. 847–857 (2013)Google Scholar
  14. 14.
    Grefenstette, E., Dinu, G., Zhang, Y.Z., Sadrzadeh, M., Baroni, M.: Multi-step regression learning for compositional distributional semantics (2013). arXiv:1301.6939
  15. 15.
    Cohen, T., Widdows, D., Schvaneveldt, R.W., Rindflesch, T.C.: Discovery at a distance: farther journeys in predication space. In: Proceedings of BIBMW-12, IEEE International Conference on Bioinformatics and Biomedicine Workshops, pp. 218–225 (2012)Google Scholar
  16. 16.
    Erk, K., McCarthy, D., Gaylord, N.: Measuring word meaning in context. Comput. Linguist. 39, 511–554 (2013)CrossRefGoogle Scholar
  17. 17.
    Elman, J.L.: An alternative view of the mental lexicon. Trends Cogn. Sci. 8, 301–306 (2004)CrossRefGoogle Scholar
  18. 18.
    Fodor, J.A.: The Language of Thought, vol. 5. Harvard University Press, Massachusetts (1975)Google Scholar
  19. 19.
    House, J.: Linguistic relativity and translation. Amsterdam Stud. Theory Hist. Linguist. Sci. 4, 69–88 (2000)Google Scholar
  20. 20.
    Trier, J.: Das sprachliche feld. Neue Jahrbucher fur Wissenschaft und Jugendbildung 10, 428–449 (1934)Google Scholar
  21. 21.
    De Saussure, F.: Course in General Linguistics. Columbia University Press, New York (2011)Google Scholar
  22. 22.
    Kožnjak, B.: Möglichkeit, wirklichkeit und quantenmechanik. Prolegomena 6, 223–252 (2007)Google Scholar
  23. 23.
    Bohm, D.: Quantum Theory. Dover Publications, New York (1989)Google Scholar
  24. 24.
    Heisenberg, W.: Physics and Philosophy: The Revolution of Modern Science. Harper & Row, New York (1958)Google Scholar
  25. 25.
    Aerts, D., Gabora, L.: A theory of concepts and their combinations I: the structure of the sets of contexts and properties. Kybernetes 34, 151–175 (2005)CrossRefGoogle Scholar
  26. 26.
    Wittek, P., Darányi, S.: Spectral composition of semantic spaces. In: Song, D., Melucci, M., Frommholz, I., Zhang, P., Wang, L., Arafat, S. (eds.) QI 2011. LNCS, vol. 7052, pp. 60–70. Springer, Heidelberg (2011) CrossRefGoogle Scholar
  27. 27.
    Darányi, S., Wittek, P.: Connecting the dots: mass, energy, word meaning, and particle-wave duality. In: Busemeyer, J.R., Dubois, F., Lambert-Mogiliansky, A., Melucci, M. (eds.) QI 2012. LNCS, vol. 7620, pp. 207–217. Springer, Heidelberg (2012) CrossRefGoogle Scholar
  28. 28.
    Mihalcea, R., Moldovan, D.I.: Word sense disambiguation based on semantic density. In: Proceedings of COLING-ACL, 36th Annual Meeting of the Association for Computational Linguistics and 17th International Conference on Computational Linguistics (1998)Google Scholar
  29. 29.
    Melucci, M.: Initial specifications for the design of information retrieval systems based on quantum detector using kinds. In: Atmanspacher, H., Haven, E., Kitto, K., Raine, D. (eds.) QI 2013. LNCS, pp. 59–70. Springer, Berlin (2013) Google Scholar
  30. 30.
    Darányi, S., Wittek, P.: Demonstrating conceptual dynamics in an evolving text collection. J. Am. Soc. Inf. Sci. Technol. 64, 2564–2572 (2013)CrossRefGoogle Scholar
  31. 31.
    Weinstein, M., Horn, D.: Dynamic quantum clustering: a method for visual exploration of structures in data. Phys. Rev. E 80, 066117 (2009)CrossRefGoogle Scholar
  32. 32.
    Neven, H., Denchev, V.S., Drew-Brook, M., Zhang, J., Macready, W.G., Rose, G.: Binary classification using hardware implementation of quantum annealing. In: Demonstrations at NIPS-09, 24th Annual Conference on Neural Information Processing Systems, pp. 1–17 (2009)Google Scholar
  33. 33.
    Trugenberger, C.A.: Probabilistic quantum memories. Phys. Rev. Lett. 87, 067901 (2001)CrossRefGoogle Scholar
  34. 34.
    Amit, D.J.: Modeling Brain Function: The World of Attractor Neural Networks. Cambridge University Press, Cambridge (1992)Google Scholar
  35. 35.
    Falissard, B.: A thought experiment reconciling neuroscience and psychoanalysis. J. Physiol Paris 105, 201–206 (2011)CrossRefGoogle Scholar
  36. 36.
    Just, M.A., Cherkassky, V.L., Aryal, S., Mitchell, T.M.: A neurosemantic theory of concrete noun representation based on the underlying brain codes. PLoS ONE 5, e8622 (2010)CrossRefGoogle Scholar
  37. 37.
    Kohonen, T.: Self-Organizing Maps. Springer, Heidelberg (2001)CrossRefzbMATHGoogle Scholar
  38. 38.
    Ultsch, A., Mörchen, F.: ESOM-maps: tools for clustering, visualization, and classification with emergent SOM. Technical report. Data Bionics Research Group, University of Marburg (2005)Google Scholar
  39. 39.
    Wittek, P.: Somoclu: an efficient distributed library for self-organizing maps (2013). arXiv:1305.1422
  40. 40.
    Budanitsky, A., Hirst, G.: Evaluating WordNet-based measures of lexical semantic relatedness. Comput. Linguist. 32, 13–47 (2006)CrossRefzbMATHGoogle Scholar
  41. 41.
    Zhang, Z., Gentile, A.L., Ciravegna, F.: Recent advances in methods of lexical semantic relatedness-a survey. Nat. Lang. Eng. 19, 411–479 (2013)CrossRefGoogle Scholar
  42. 42.
    Newman, D., Lau, J.H., Grieser, K., Baldwin, T.: Automatic evaluation of topic coherence. In: Proceedings of NAACL-HLT-10, Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Association for Computational Linguistics, pp. 100–108 (2010)Google Scholar
  43. 43.
    Wittek, P., Ravenek, W.: Supporting the exploration of a corpus of 17th-century scholarly correspondences by topic modeling. In: Proceedings of SDH-11, Supporting Digital Humanities: Answering the Unaskable (2011)Google Scholar
  44. 44.
    Kievit-Kylar, B., Jones, M.N.: Visualizing multiple word similarity measures. Behav. Res. Meth. 44, 656–674 (2012)CrossRefGoogle Scholar
  45. 45.
    Weeds, J., Weir, D.: Co-occurrence retrieval: a flexible framework for lexical distributional similarity. Comput. Linguist. 31, 439–475 (2005)CrossRefzbMATHGoogle Scholar
  46. 46.
    Rohde, D.L., Gonnerman, L.M., Plaut, D.C.: An improved model of semantic similarity based on lexical co-occurrence. Commun. ACM 8, 627–633 (2006)Google Scholar
  47. 47.
    Clarke, D.: A context-theoretic framework for compositionality in distributional semantics. Comput. Linguist. 38, 41–71 (2012)CrossRefGoogle Scholar
  48. 48.
    Bruni, E., Uijlings, J., Baroni, M., Sebe, N.: Distributional semantics with eyes: using image analysis to improve computational representations of word meaning. In: Proceedings of MM-12, 20th ACM International Conference on Multimedia, pp. 1219–1228 (2012)Google Scholar
  49. 49.
    Ursino, M., Cuppini, C., Magosso, E.: A computational model of the lexical-semantic system based on a grounded cognition approach. Embodied and Grounded Cognition 1 (2010)Google Scholar

Copyright information

© Springer International Publishing Switzerland 2015

Authors and Affiliations

  • Peter Wittek
    • 1
  • Sándor Darányi
    • 1
    Email author
  • Ying-Hsang Liu
    • 2
  1. 1.University of BoråsBoråsSweden
  2. 2.Charles Sturt UniversityWagga WaggaAustralia

Personalised recommendations