<?xml version="1.0" encoding="UTF-8"?>
<article xmlns:xlink="http://www.w3.org/1999/xlink" dtd-version="1.4" article-type="research-article" xml:lang="en"><front><journal-meta><journal-title-group><journal-title xml:lang="ru">Вестник Волгоградского государственного университета. Серия 2. Языкознание</journal-title></journal-title-group><journal-id journal-id-type="issn">1998-9911</journal-id><journal-id journal-id-type="eissn">2409-1979</journal-id></journal-meta><article-meta><article-id pub-id-type="doi">10.15688/jvolsu2.2024.5.2</article-id><title-group><article-title xml:lang="ru">Теория метаграфов как основа моделирования актуального медиадискурса</article-title><trans-title-group xml:lang="en"><trans-title>Metagraph Theory as a Basis for Modeling Relevant Media Discourse</trans-title></trans-title-group></title-group><contrib-group><contrib contrib-type="author"><name><surname>Гапанюк</surname><given-names>Юрий Евгеньевич</given-names></name><name-alternatives><name xml:lang="ru"><surname>Гапанюк</surname><given-names>Юрий Евгеньевич</given-names></name><name xml:lang="en"><surname>Gapanyuk</surname><given-names>Yuriy</given-names></name></name-alternatives><xref ref-type="aff" rid="aff1"/><email>gapyu@bmstu.ru</email><contrib-id contrib-id-type="orcid">0000-0001-9005-8174</contrib-id></contrib><aff-alternatives id="aff1"><aff><institution xml:lang="en">Bauman Moscow State Technical University (Moscow, Russian Federation)</institution></aff><aff><institution xml:lang="ru">Московский государственный технический университет им. Н.Э. Баумана (Москва, Российская Федерация)</institution></aff></aff-alternatives></contrib-group><pub-date pub-type="epub" iso-8601-date="2024-12-27"><day>27</day><month>12</month><year>2024</year></pub-date><volume>23</volume><issue>5</issue><fpage>20</fpage><lpage>30</lpage><history><date date-type="received" iso-8601-date="2024-03-13"><day>13</day><month>03</month><year>2024</year></date><date date-type="accepted" iso-8601-date="2024-06-24"><day>24</day><month>06</month><year>2024</year></date></history><permissions><license><license-p xml:lang="ru">CC BY 4.0</license-p></license></permissions><abstract xml:lang="ru"><p>Статья посвящена моделированию медиадискурса на основе комбинации модели сложных графов и многомерной модели. Несмотря на значительные достижения в области нейросетевой обработки текста, задача моделирования текстов и медиадискурса остается актуальной. Сегодня большие языковые модели не могут рассматриваться как надежная модель дискурса по причине того, что они подвержены галлюцинациям, которые составляют особенности обучения модели и которые трудно диагностировать и устранить на практике. Базовой моделью в рамках предлагаемого подхода является аннотируемая метаграфовая модель, важнейшим элементом этой модели – метавершина. Метавершины со своими собственными атрибутами и связями с другими вершинами соответствует принципу эмерджентности. Для преобразования метаграфов используются метаграфовые агенты. Многомерная метаграфовая модель представляет собой комбинацией классической многомерной модели и аннотируемой метаграфовой модели и позволяет хранить в ячейках гиперкуба сложные описания в форме метаграфов. Многомерная метаграфовая модель может естественным образом применяться как модель текстового и медиадискурса. К значимым недостаткам текущей версии предложенной модели относится отсутствие системы семантических проверок дискурса. Разработка системы таких проверок формирует отдельное направление дальнейших исследований.</p></abstract><trans-abstract xml:lang="en"><p>This article is devoted to modeling media discourse based on a combination of a complex graph model and a multidimensional model. Despite significant advances in the field of neural network text processing, the task of modeling text and media discourse remains relevant. Large language models cannot be considered as a reliable discourse model, due to the fact that they are susceptible to hallucinations, which are features of model training and are difficult to diagnose and eliminate in practice. The basic model within the framework of the proposed approach is an annotated metagraph model; the main element of this model is the metavertex. The presence of metavertices with their own attributes and connections with other vertices corresponds to the principle of emergence, that is, giving the concept a new quality, the irreducibility of the concept to the sum of its component parts. Metagraph agents are used to transform metagraphs. A multidimensional metagraph model is a combination of a classical multidimensional model and an annotated metagraph model and allows complex descriptions in the form of metagraphs to be stored in hypercube cells. The multidimensional metagraph model can naturally be considered as a model of text and media discourse. The main drawback of the current version of the proposed model is the lack of a semantic discourse check system. Designing this system is the main direction for the development of further research.</p></trans-abstract><kwd-group xml:lang="en"><kwd>metagraph</kwd><kwd>hypercube</kwd><kwd>media discourse</kwd><kwd>text processing</kwd><kwd>metavertex</kwd><kwd>metaedge</kwd><kwd>metagraph agent</kwd><kwd>multidimensional metagraph model</kwd></kwd-group><kwd-group xml:lang="ru"><kwd>обработка текстов</kwd><kwd>метаграф</kwd><kwd>метавершина</kwd><kwd>метаребро</kwd><kwd>метаграфовый агент</kwd><kwd>многомерная метаграфовая модель</kwd><kwd>гиперкуб</kwd><kwd>медиадискурс</kwd></kwd-group></article-meta></front><back><ref-list><ref id="ref1"><mixed-citation xml:lang="ru">Basu A., Blanning R.W., 2007. Metagraphs and Their Applications. Springer Science &amp; Business Media. 173 p.</mixed-citation></ref><ref id="ref2"><mixed-citation xml:lang="ru">Codd E.F., 1993. Providing OLAP (On-Line Analytical Processing) to User-Analysts: An IT Mandate. URL: http://www.arborsoft.com/papers/coddTOC.html</mixed-citation></ref><ref id="ref3"><mixed-citation xml:lang="ru">Gapanyuk Y., 2019. Metagraph Approach to the Information-Analytical Systems Development. Actual Problems of System and Software Engineering (APSSE 2019). CEUR Workshop Proceedings, vol. 2514, pp. 428-439.</mixed-citation></ref><ref id="ref4"><mixed-citation xml:lang="ru">Gapanyuk Y., 2021. The Development of the Metagraph Data and Knowledge Model. Advances in Fuzzy Systems and Soft Computing: Selected Contributions to the 10th International Conference on “Integrated Models and Soft Computing in Artificial Intelligence (IMSC-2021), pp. 1-7.</mixed-citation></ref><ref id="ref5"><mixed-citation xml:lang="ru">Feng Z., 2023. Formal Models of Discourse Analysis. Formal Analysis for Natural Language Processing: A Handbook. Singapore, Springer Nature Singapore, pp. 597-633.</mixed-citation></ref><ref id="ref6"><mixed-citation xml:lang="ru">Hou S., Zhang S., Fei C., 2020. Rhetorical Structure Theory: A Comprehensive Review of Theory, Parsing Methods and Applications. Expert Systems with Applications, vol. 157, no. 113421.</mixed-citation></ref><ref id="ref7"><mixed-citation xml:lang="ru">Khalil A., Belaissaoui M., 2022. A Graph-Oriented Framework for Online Analytical Processing. International Journal of Advanced Computer Science and Applications, vol. 13, no. 5, pp. 547-555. DOI: 10.14569/IJACSA.2022.0130564</mixed-citation></ref><ref id="ref8"><mixed-citation xml:lang="ru">Liu L., Lin X., Joty S., Han S., Bing L., 2019. Hierarchical Pointer Net Parsing. DOI: 10.48550/arXiv.1908.11571</mixed-citation></ref><ref id="ref9"><mixed-citation xml:lang="ru">Maziero E.G., Jorge M.L.D.R.C., Pardo T.A.S., 2014. Revisiting Cross-Document Structure Theory for Multi-Document Discourse Parsing. Information Processing &amp; Management, vol. 50, no. 2, pp. 297-314.</mixed-citation></ref><ref id="ref10"><mixed-citation xml:lang="ru">Minaee S., Mikolov T., Nikzad N., Chenaghlu M., Socher R., Amatriain X., Gao J., 2024. Large Language Models: A Survey. DOI: 10.48550/arXiv.2402.06196</mixed-citation></ref><ref id="ref11"><mixed-citation xml:lang="ru">Pilehvar M.T., Camacho-Collados J., 2020. Embeddings in Natural Language Processing: Theory and Advances in Vector Representations of Meaning. Morgan &amp; Claypool Publishers, p. 175.</mixed-citation></ref><ref id="ref12"><mixed-citation xml:lang="ru">Schuetz C.G., Bozzato L., Neumayr B., Schrefl M., Serafini L., 2021. Knowledge Graph OLAP. Semantic Web, vol. 12, no. 4, pp. 649-683. DOI: 10.3233/SW-200419</mixed-citation></ref><ref id="ref13"><mixed-citation xml:lang="ru">Webber B., Prasad R., Lee A., Joshi A., 2019. The Penn Discourse Treebank 3.0 Annotation Manual. Philadelphia, University of Pennsylvania, p. 81. URL: https://catalog.ldc.upenn.edu/docs/LDC2019T05/PDTB3-Annotation-Manual.pdf</mixed-citation></ref><ref id="ref14"><mixed-citation xml:lang="ru">Yao J.Y., Ning K.P., Liu Z.H., Ning M.N., Yuan L., 2023. LLM Lies: Hallucinations Are Not Bugs, but Features as Adversarial Examples. DOI: 10.48550/arXiv.2310.01469</mixed-citation></ref><ref id="ref15"><mixed-citation xml:lang="en">Basu A., Blanning R.W., 2007. Metagraphs and Their Applications. Springer Science &amp; Business Media. 173 p.</mixed-citation></ref><ref id="ref16"><mixed-citation xml:lang="en">Codd E.F., 1993. Providing OLAP (On-Line Analytical Processing) to User-Analysts: An IT Mandate. URL: http://www.arborsoft.com/papers/coddTOC.html</mixed-citation></ref><ref id="ref17"><mixed-citation xml:lang="en">Gapanyuk Y., 2019. Metagraph Approach to the Information-Analytical Systems Development. Actual Problems of System and Software Engineering (APSSE 2019). CEUR Workshop Proceedings, vol. 2514, pp. 428-439.</mixed-citation></ref><ref id="ref18"><mixed-citation xml:lang="en">Gapanyuk Y., 2021. The Development of the Metagraph Data and Knowledge Model. Advances in Fuzzy Systems and Soft Computing: Selected Contributions to the 10th International Conference on “Integrated Models and Soft Computing in Artificial Intelligence (IMSC-2021), pp. 1-7.</mixed-citation></ref><ref id="ref19"><mixed-citation xml:lang="en">Feng Z., 2023. Formal Models of Discourse Analysis. Formal Analysis for Natural Language Processing: A Handbook. Singapore, Springer Nature Singapore, pp. 597-633.</mixed-citation></ref><ref id="ref20"><mixed-citation xml:lang="en">Hou S., Zhang S., Fei C., 2020. Rhetorical Structure Theory: A Comprehensive Review of Theory, Parsing Methods and Applications. Expert Systems with Applications, vol. 157, no. 113421.</mixed-citation></ref><ref id="ref21"><mixed-citation xml:lang="en">Khalil A., Belaissaoui M., 2022. A Graph-Oriented Framework for Online Analytical Processing. International Journal of Advanced Computer Science and Applications, vol. 13, no. 5, pp. 547-555. DOI: 10.14569/IJACSA.2022.0130564</mixed-citation></ref><ref id="ref22"><mixed-citation xml:lang="en">Liu L., Lin X., Joty S., Han S., Bing L., 2019. Hierarchical Pointer Net Parsing. DOI: 10.48550/arXiv.1908.11571</mixed-citation></ref><ref id="ref23"><mixed-citation xml:lang="en">Maziero E.G., Jorge M.L.D.R.C., Pardo T.A.S., 2014. Revisiting Cross-Document Structure Theory for Multi-Document Discourse Parsing. Information Processing &amp; Management, vol. 50, no. 2, pp. 297-314.</mixed-citation></ref><ref id="ref24"><mixed-citation xml:lang="en">Minaee S., Mikolov T., Nikzad N., Chenaghlu M., Socher R., Amatriain X., Gao J., 2024. Large Language Models: A Survey. DOI: 10.48550/arXiv.2402.06196</mixed-citation></ref><ref id="ref25"><mixed-citation xml:lang="en">Pilehvar M.T., Camacho-Collados J., 2020. Embeddings in Natural Language Processing: Theory and Advances in Vector Representations of Meaning. Morgan &amp; Claypool Publishers, p. 175.</mixed-citation></ref><ref id="ref26"><mixed-citation xml:lang="en">Schuetz C.G., Bozzato L., Neumayr B., Schrefl M., Serafini L., 2021. Knowledge Graph OLAP. Semantic Web, vol. 12, no. 4, pp. 649-683. DOI: 10.3233/SW-200419</mixed-citation></ref><ref id="ref27"><mixed-citation xml:lang="en">Webber B., Prasad R., Lee A., Joshi A., 2019. The Penn Discourse Treebank 3.0 Annotation Manual. Philadelphia, University of Pennsylvania, p. 81. URL: https://catalog.ldc.upenn.edu/docs/LDC2019T05/PDTB3-Annotation-Manual.pdf</mixed-citation></ref><ref id="ref28"><mixed-citation xml:lang="en">Yao J.Y., Ning K.P., Liu Z.H., Ning M.N., Yuan L., 2023. LLM Lies: Hallucinations Are Not Bugs, but Features as Adversarial Examples. DOI: 10.48550/arXiv.2310.01469</mixed-citation></ref></ref-list></back></article>
