Abstract
The paper suggests and develops a method for creating cognitive patterns for well-formalizable problems described in a natural language. The method takes into account the full set of human cognitive abilities: the understanding of a natural language in the light of a well-formalizable problem, its formalization for an automatic solution, a graphical display of the solution, and its psychological aspects. The method is focused on a holistic approach to applied artificial intelligence systems considered in terms of interdisciplinarity. We have conducted an experimental study of the method capabilities on a set of geometric problems. Our experiment has included the modification of the source text at the level of morphology, syntax, and significant objects of a geometric problem followed by the preparation of a drawing. We have suggested an extension of the experiment to the problems with physical content.
Keywords
This study was supported by the Russian Foundation for Basic Research (project No. 18-07-00098 А, No. 20-07-00439 A, No. 18-29-03088 A).
This is a preview of subscription content, log in via an institution.
Buying options
Tax calculation will be finalised at checkout
Purchases are for personal use only
Learn about institutional subscriptionsReferences
Kuhn, T.: The Structure of Scientific Revolutions. Chicago, 1962; 2edn. Chicago, 1970. HOL interactive theorem prover (2018)
Lakoff, G.: Metaphors We Live By. University of Chicago Press. 2003 edition contains an 'Afterword', 2003 (1980)
Naidenova, X., Kurbatov, S., Ganapolsky, V.: Cognitive models in planimetric task text processing. Int. J. Cogn. Res. Sci. Eng. Educ. (ISSN: 2334–847X)
Kurbatov, S.S., Fominykh, I.B., Vorobyev, A.B.: ontology-controlled geometric solver. In: Kuznetsov, S.O., Panov, A.I., Yakovlev, K.S. (eds.) Artificial Intelligence. RCAI 2020. LNCS, vol. 12412. Springer, Cham (2020). https://doi.org/10.1007/978-3-030-59535-7_19
Polya, G.: Mathematical Discovery: On Understanding, Learning and Teaching Problem Solving, p. 432. Wiley, Hoboken (1981)
Dynamic mathematics with JavaScript, JSXGraph is a cross-browser JavaScript library for interactive geometry, function plotting, charting, and data visualization in the web browser. – http://jsxgraph.uni-bayreuth.de/wp/index.html
MathJax is a cross-browser JavaScript library that displays mathematical notation in web browsers, using MathML, LaTeX and ASCIIMathML markup. – https://github.com/mathjax/MathJax/releases/tag/3.1.2
Screenshot-1. http://www.eia--dostup.ru/APP-1.pdf
Screenshot-2. http://www.eia--dostup.ru/APP-2.pdf
Kulanin, E.D.: 3000 konkursnyh zadach po matematike. Geometriya, Ileksa (2018)
Schenk, R.C., Goldman, N.M., Rieger, C.J., Riesbeck, C.K.: Conceptual information processing. Norh-Holland Publishing Company, Amsterdam (1975)
Winograd, T.: Understanding Natural Language. Academic Press, New York (1972)
Sergeeva, T.F., Shabanova, M.V., Grozdev, S.I.: Fundamentals of Dynamic Geometry, p. 152. Publishing house ASOU, Russia (2016).(in Russian)
Sergey, S., Kurbatov, I.B., Fominykh, A.B.: Vorobyev applied aspects of the integrated problem solving system with natural language interface. In: Conference: 2020 V International Conference on Information Technologies in Engineering Education ( Inforino ), IEEE Computer Society (2020)
Gan, W., Yu, X.: Automatic understanding and formalization of natural language geometry problems using syntax-semantics models. Int. J. Innov. Comput. Inf. Control ICIC 14(1), 83–98 (2018)
Seo, M., Hajishirzi, H., Farhadi, A., Etzioni, O., Malcolm, C.: Solving geometry problems: combining text and diagram interpretation. http://geometry.allenai.org/assets/emnlp2015.pdf
Shi, S., Wang, Y., Lin, C.-Y., Liu, X., Yong Rui, Y:. Automatically solving number word problems by semantic parsing and reasoning. In: Proceedings of the 2015 Conference on Empirical Methods in Natural Language Processing. Lisbon, Portugal, 17–21 September, pp. 1132–1142 (2015)
Wang, K., Su, Z.: Automated geometry theorem proving for human-readable proofs. In: Proceedings of the Twenty-Fourth International Joint Conference on Artificial Intelligence. Buenos Aires, Argentina, 25–31 July (2015)
AllenNLP 2.5.0. https://pypi.org/project/allennlp/
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2021 Springer Nature Switzerland AG
About this paper
Cite this paper
Kurbatov, S., Fominykh, I., Vorobyev, A. (2021). Cognitive Patterns for Semantic Presentation of Natural-Language Descriptions of Well-Formalizable Problems. In: Kovalev, S.M., Kuznetsov, S.O., Panov, A.I. (eds) Artificial Intelligence. RCAI 2021. Lecture Notes in Computer Science(), vol 12948. Springer, Cham. https://doi.org/10.1007/978-3-030-86855-0_22
Download citation
DOI: https://doi.org/10.1007/978-3-030-86855-0_22
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-86854-3
Online ISBN: 978-3-030-86855-0
eBook Packages: Computer ScienceComputer Science (R0)