Word in technogenic multidimensional space
https://doi.org/10.17726/philIT.2022.1.2
Abstract
Today, artificial intelligence is actively mastering natural languages, becoming an interlocutor and partner of human in various aspects of activity. However, the symbolic approach, which implies the transfer of rules and logic, has failed, the number of rules and exceptions of the language does not allow its formalization, so modern «deep learning» of artificial neural networks involves an independent search for patterns in extensive databases. During training, artificial intelligence puts a word into a sentence so that the syntagmatic relationships are as close as possible to those of the target word in the base, taking into account both the semantic relationships of words and the relationships between words in the sequence of presentation. The «language» of information technologies is digital. During natural language processing, words are represented in vector form as a sequence of numbers. The idea of representing words mathematically is familiar to people and is usually associated with logical consistency. Visualization of the position of words in a multidimensional space created by artificial intelligence demonstrates a number of patterns, obvious semantic and syntactic relationships, but the essence of other relationships between words is not obvious. The mathematical representation of words, created by artificial intelligence, can allow you to look at the language from a new non-human point of view.
About the Author
D. S. Bylieva
Peter the Great St. Petersburg Polytechnic University
Russian Federation
Russian Federation
Bylieva Daria - PhD, associated professor
St. Petersburg
References
1. Ullmann L. The quasi-other as a Sobject // Technology and Language. – 2022. – № 1(3). – P. 76-81. – URL: https://doi.org/10.48417/technolang.2022.01.08.
2. Bylieva D. Language of AI // Technology and Language. – 2022. – № 1(3). – P. 111-126. – URL: https://doi.org/10.48417/technolang.2022.01.11.
3. Chomsky N. Syntactic Structures. – Berlin: Mouton, 1957. – 116 p. – URL: https://doi.org/10.1515/9783112316009.
4. Crystal D. The lure of words // The Oxford handbook of the word. – Oxford: Oxford University Press, 2015. – P. 23-28.
5. Lebedev S.A. Mathematics and technical sciences are the basis of the integrity of modern scientific knowledge // Gumanitarnyj vestnik. – 2018. – Vol. 72(10). – S. 22-48.
6. Shtejngauz G. Tasks and reflections. – M.: Mir, 1974. – 168 s.
7. Hähnle R. Program and Code // Technology and Language. – 2022. – № 3(2). – URL: https://doi.org/10.48417/technolang.2022.02.06.
8. Cambria E., White B. Jumping NLP Curves: A Review of Natural Language Processing Research [Review Article] // IEEE Computational Intelligence Magazine. – 2014. – № 2(9). – P. 48-57. – URL: https://doi.org/10.1109/MCI.2014.2307227.
9. Lake B. M., Ullman T.D., Tenenbaum J.B., Gershman S. J. Building machines that learn and think like people // Behavioral and Brain Sciences. 2017. – (40). – e253. – URL: https://doi.org/10.1017/S0140525X16001837.
10. Spelke E. S., Gutheil G. & Van de Walle G. The development of object perception // An invitation to cognitive science: vol. 2. Visual cognition. 2nd ed. Bradford, 1995. – P. 297-330.
11. Spelke E. S., Kinzler K.D. Core knowledge // Developmental Science. 2007. № 1(10). P. 89-96. – URL: https://doi.org/10.1111/j.1467-7687.2007.00569.x.
12. Capone L. Which Theory of Language for Deep Neural Networks? Speech and Cognition in Humans and Machines // Technology and Languag. – 2021. – № 4(2). – P. 29-60. – URL: https://doi.org/10.48417/technolang.2021.04.03.
13. Kuznecov V. G. I Intensional syllogistics of G.V. Leibniz and its role in the history of logic // Vestnik Moskovskogo universiteta. Seriia 7. Filosofiia. – 2017. – Vol. 4. – S. 3-18.
14. Lejbnic G.V. Works in four volumes: Vol. 3. – M.: Mysl’, 1984. – 734 s.
15. Nordmann A. Linguistic thinking and language thinking in Georg Christoph Lichtenberg: “where … any error against the truth would also be grammatical” // Semioticheskie issledovaniia. – 2021. – Vol. 4. – S. 29-38.– URL: https://doi.org/10.18287/2782-2966-2021-1-4-29-38.
16. Fritz G. Theories of meaning change: An overview // Semantics – Typology, Diachrony and Processing. De Gruyter, 2019. – P. 113-146.
17. Faraj G. A.K. Semantic Field of Utterances in «‘Healthy Living Guide’» // International Journal on Humanities and Social Sciences. – 2022. – № 32. – P. 186-197. – URL: https://doi.org/10.33193/IJoHSS.32.2022.400.
18. Trier J. Der deutsche Wortschatz im Sinnbezirk des Verstandes. Von den Anfangen bis zum Beginn des. Jahrhunderts. – Heidelberg: Carl Winter Universitatsverlag, 1973.
19. Gärdenfors P. Conceptual spaces: The geometry of thought. – Cambridge, MA: MIT Press, 2009.
20. Gärdenfors P. Semantics Based on Conceptual Spaces // Logic and Its Applications. ICLA 2011. Lecture Notes in Computer Science, vol 6521. Cham: Springer, 2011. – P. 1-11. – URL: https://doi.org/10.1007/978-3-642-18026-2_1.
21. Gärdenfors P., Zenker F. Conceptual Spaces at Work // Applications of Conceptual Spaces, Synthese Library 359. – Cham: Springer, 2015. – P. 3-13. – URL: https://doi.org/ 10.1007/978-3-319-15021-5_1.
22. Banaee H., Loutfi A. Using Conceptual Spaces to Model Domain Knowledge in Data-to-Text Systems // Proceedings of the 8th International Natural Language Generation Conference (INLG). – Cham: Springer, 2014. – P. 11-15. URL: https://doi.org/10.3115/v1/W14-4403.
23. Mikolov T., Chen K., Corrado G., Dean J. Efficient estimation of word representations in vector space // 1st International Conference on Learning Representations, ICLR2013 – Workshop Track Proceedings. ICLR, 2013. – ArXiv ID: 1301.3781.
24. Prepare Your Data. – URL: https://developers.google.com/machinelearning/guides/text-classification/step-3.
25. Sundararaman D., Subramanian V., Wang G., Si S., Shen D., Wang D., Carin L. Syntax-Infused Transformer and BERT models for Machine Translation and Natural Language Understanding. 2019. – ArXiv ID: 1911.06156.
26. Mikolov T., Sutskever I., Chen K., Corrado G. S., Dean J. Distributed Representations of Words and Phrases and their Compositionality // Advances in Neural Information Processing Systems 26 (NIPS2013). Neurips, 2013. – P. 3111-3119. – URL: https://proceedings.neurips.cc/paper/2013/file/9aa42b31882ec039965f3c4923ce901b-Paper.pdf.
27. Alammar J. The Illustrated Word2vec. – 2019. – URL: https://jalammar.github.io/illustrated-word2vec.
28. Church K., Liberman M. The Future of Computational Linguistics: On Beyond Alchemy // Frontiers in Artificial Intelligence. – 2021. – Vol. 4. – URL: https://doi.org/10.3389/frai.2021.625341.
Review
For citations:
Bylieva D.S. Word in technogenic multidimensional space. Philosophical Problems of IT & Cyberspace (PhilIT&C). 2022;(1):18-33. (In Russ.) https://doi.org/10.17726/philIT.2022.1.2
Views:
509
Email this article 