<?xml version="1.0" encoding="UTF-8"?>
<!DOCTYPE article PUBLIC "-//NLM//DTD JATS (Z39.96) Journal Publishing DTD v1.3 20210610//EN" "JATS-journalpublishing1-3.dtd">
<article article-type="research-article" dtd-version="1.3" xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink" xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance" xml:lang="ru"><front><journal-meta><journal-id journal-id-type="publisher-id">linmgou</journal-id><journal-title-group><journal-title xml:lang="ru">Вопросы современной лингвистики</journal-title><trans-title-group xml:lang="en"><trans-title>Key Issues of Contemporary Linguistics</trans-title></trans-title-group></journal-title-group><issn pub-type="ppub">2949-5059</issn><issn pub-type="epub">2949-5075</issn><publisher><publisher-name>Federal State University of Education</publisher-name></publisher></journal-meta><article-meta><article-id pub-id-type="doi">10.18384/2949-5075-2025-1-67-82</article-id><article-id custom-type="elpub" pub-id-type="custom">linmgou-1732</article-id><article-categories><subj-group subj-group-type="heading"><subject>Research Article</subject></subj-group><subj-group subj-group-type="section-heading" xml:lang="ru"><subject>ТЕОРЕТИЧЕСКАЯ, ПРИКЛАДНАЯ И СРАВНИТЕЛЬНО-СОПОСТАВИТЕЛЬНАЯ ЛИНГВИСТИКА</subject></subj-group><subj-group subj-group-type="section-heading" xml:lang="en"><subject>THEORETICAL, APPLIED AND COMPARATIVE LINGUISTICS</subject></subj-group></article-categories><title-group><article-title>Инклюзивная диалоговая система нового поколения: лингвистический аспект</article-title><trans-title-group xml:lang="en"><trans-title>Inclusive next-generation dialogue system: linguistic aspect</trans-title></trans-title-group></title-group><contrib-group><contrib contrib-type="author" corresp="yes"><contrib-id contrib-id-type="orcid">https://orcid.org/0000-0002-8474-0262</contrib-id><name-alternatives><name name-style="eastern" xml:lang="ru"><surname>Фирсанова</surname><given-names>В. И.</given-names></name><name name-style="western" xml:lang="en"><surname>Firsanova</surname><given-names>V. I.</given-names></name></name-alternatives><bio xml:lang="ru"><p>Фирсанова Виктория Игоревна – аспирант кафедры математической лингвистики</p><p>г. Санкт-Петербург</p></bio><bio xml:lang="en"><p>Viktorya I. Firsanova – Postgraduate Student, Department of mathematical Linguistics</p><p>Saint Petersburg</p></bio><email xlink:type="simple">st085687@student.spbu.ru</email><xref ref-type="aff" rid="aff-1"/></contrib></contrib-group><aff-alternatives id="aff-1"><aff xml:lang="ru"><institution>Санкт-Петербургский государственный университет</institution><country>Россия</country></aff><aff xml:lang="en"><institution>Saint-Petersburg State University</institution><country>Russian Federation</country></aff></aff-alternatives><pub-date pub-type="collection"><year>2025</year></pub-date><pub-date pub-type="epub"><day>13</day><month>05</month><year>2025</year></pub-date><volume>0</volume><issue>1</issue><fpage>67</fpage><lpage>82</lpage><permissions><copyright-statement>Copyright &amp;#x00A9; Фирсанова В.И., 2025</copyright-statement><copyright-year>2025</copyright-year><copyright-holder xml:lang="ru">Фирсанова В.И.</copyright-holder><copyright-holder xml:lang="en">Firsanova V.I.</copyright-holder><license xml:lang="ru" license-type="creative-commons-attribution" xlink:href="https://creativecommons.org/licenses/by/4.0/" xlink:type="simple"><license-p>Данная работа распространяется под лицензией Creative Commons Attribution 4.0.</license-p></license><license xml:lang="en" license-type="creative-commons-attribution" xlink:href="https://creativecommons.org/licenses/by/4.0/" xlink:type="simple"><license-p>This work is licensed under a Creative Commons Attribution 4.0 License.</license-p></license></permissions><self-uri xlink:href="https://www.linguamgou.ru/jour/article/view/1732">https://www.linguamgou.ru/jour/article/view/1732</self-uri><abstract><sec><title>Цель</title><p>Цель. Выявление стратегии разработки языковых моделей с помощью искусственного интеллекта для поддержки инклюзии людей с ментальными нарушениями. </p></sec><sec><title>Процедура и методы</title><p>Процедура и методы. В исследовании сравниваются два подхода к построению диалоговых систем: вопросно-ответные системы на основе извлечения информации и генеративные модели. Собрана коллекция текстов на тему инклюзивного образования. Методами нейросетевого трансферного обучения также создан комплекс вопросно-ответных систем для анализа производительности рассматриваемых подходов. Проведён лингвистический анализ собранной коллекции данных и результатов работы диалоговой системы. </p></sec><sec><title>Результаты</title><p>Результаты. Исследование показало, что оба подхода к построению диалоговых систем имеют свои преимущества и ограничения. Вопросно-ответные системы на основе извлечения информации обеспечивают высокую релевантность ответов. Генеративные модели, в свою очередь, обладают большей гибкостью в широком контексте. Лингвистический анализ показал, что для достижения наилучших результатов целесообразно комбинировать оба подхода, используя сильные стороны каждого из них в зависимости от конкретной задачи и контекста взаимодействия. </p><p>Теоретическая и/или практическая значимость заключается в развитии теории диалоговых систем, углублении понимания взаимодействия между структурными и семантическими аспектами языка и их влияния на эффективность различных подходов к созданию диалоговых систем, а также в возможности применения результатов исследования в образовательной системе.</p></sec></abstract><trans-abstract xml:lang="en"><sec><title>Aim</title><p>Aim. To identify strategies for developing language models using artificial intelligence to support the inclusion of people with mental disabilities.</p></sec><sec><title>Methodology</title><p>Methodology. The study compares two approaches to building dialogue systems: information retrieval question-answering systems and generative question-answering. A collection of texts on inclusive education was compiled. Additionally, a complex of question-answering systems was created using neural network transfer learning methods to analyze the performance of the approaches. A linguistic analysis of the collected data and the results of the dialogue system was conducted.</p></sec><sec><title>Results</title><p>Results. The study showed that both approaches to building dialogue systems have their advantages and limitations. Information retrieval question-answering systems provide high answer relevance. Generative models offer greater flexibility in a broader context. Linguistic analysis revealed that for optimal results, it is advisable to combine both approaches, leveraging the strengths of each depending on the specific task and interaction context.</p></sec><sec><title>Research implications</title><p>Research implications. The significance lies in the development of dialogue system theory, deepening the understanding of the interaction between structural and semantic aspects of language and their impact on the effectiveness of different approaches to creating dialogue systems, as well as the possibility of applying the research results in the educational system.</p></sec></trans-abstract><kwd-group xml:lang="ru"><kwd>генеративные модели</kwd><kwd>диалоговые системы</kwd><kwd>инклюзивное образование</kwd><kwd>лингвистический анализ</kwd><kwd>нейросетевые модели</kwd></kwd-group><kwd-group xml:lang="en"><kwd>dialogue systems</kwd><kwd>generative models</kwd><kwd>inclusive education</kwd><kwd>linguistic analysis</kwd><kwd>neural network models</kwd></kwd-group></article-meta></front><back><ref-list><title>References</title><ref id="cit1"><label>1</label><citation-alternatives><mixed-citation xml:lang="ru">World Report on Disability / World Health Organization; The World Bank. Geneva, Switzerland; Malta: World Health Organization, 2011. 325 + XXIV p.</mixed-citation><mixed-citation xml:lang="en">World Report on Disability (2011). Geneva, Switzerland; Malta: World Health Organization.</mixed-citation></citation-alternatives></ref><ref id="cit2"><label>2</label><citation-alternatives><mixed-citation xml:lang="ru">Борисов П. М. Вербальная характеристика концепта деструктивной личности // Вестник Московского государственного областного университета. Серия: Лингвистика. 2010. № 2. С. 78–92.</mixed-citation><mixed-citation xml:lang="en">Borisov, P. M. (2010). Verbal description destructive personality concept. In: Bulletin of the Moscow Region State University. Series: Linguistics, 2, 78–92 (in Russ.).</mixed-citation></citation-alternatives></ref><ref id="cit3"><label>3</label><citation-alternatives><mixed-citation xml:lang="ru">Leifler E. Educational inclusion for students with neurodevelopmental conditions: Thesis for Doctoral Degree (Ph. D.). Stockholm, 2022. 167 p.</mixed-citation><mixed-citation xml:lang="en">Leifler, E. (2022). Educational inclusion for students with neurodevelopmental conditions [dissertation]. Stockholm.</mixed-citation></citation-alternatives></ref><ref id="cit4"><label>4</label><citation-alternatives><mixed-citation xml:lang="ru">Eshghie M., Eshgie M. ChatGPT as a Therapist Assistant: A Suitability Study [Электронный ресурс] // arXiv: [сайт]. URL: https://arxiv.org/abs/2304.09873 (дата обращения: 13.09.2023). DOI: 10.48550/arXiv.2304.09873.</mixed-citation><mixed-citation xml:lang="en">Eshghie, M. &amp; Eshgie, M. (2023). ChatGPT as a Therapist Assistant: A Suitability Study. In: arXiv. URL: https://arxiv.org/abs/2304.09873 (accessed: 13.09.2023). DOI: 10.48550/arXiv.2304.09873.</mixed-citation></citation-alternatives></ref><ref id="cit5"><label>5</label><citation-alternatives><mixed-citation xml:lang="ru">Gillespie A., Best C., O'Neill B. Cognitive Function and Assistive Technology for Cognition: a Systematic Review // Journal of the International Neuropsychological Society. 2012. Vol. 18. Iss. 1. P. 1–19. DOI: 10.1017/S1355617711001548.</mixed-citation><mixed-citation xml:lang="en">Gillespie, A., Best, C. &amp; O'Neill, B. (2012). Cognitive Function and Assistive Technology for Cognition: a Systematic Review. In: Journal of the International Neuropsychological Society, 18 (1), 1–19. DOI: 10.1017/S1355617711001548.</mixed-citation></citation-alternatives></ref><ref id="cit6"><label>6</label><citation-alternatives><mixed-citation xml:lang="ru">Ruder S. Neural Transfer Learning for Natural Language Processing: A thesis submitted in partial fulfillment for the degree of Doctor of Philosophy. Galway, 2019. 329 p.</mixed-citation><mixed-citation xml:lang="en">Ruder, S. (2019). Neural Transfer Learning for Natural Language Processing: A thesis submitted in partial fulfillment for the degree of Doctor of Philosophy. Galway.</mixed-citation></citation-alternatives></ref><ref id="cit7"><label>7</label><citation-alternatives><mixed-citation xml:lang="ru">SQuAD: 100,000+ Questions for Machine Comprehension of Text / P. Rajpurkar, J. Zhang, K. Lopyrev, P. Liang // Proceedings of the 2016 Conference on Empirical Methods in Natural Language Processing. Austin, Texas: Association for Computational Linguistics, 2016. P. 2383–2392. DOI: 10.18653/v1/D16-1264.</mixed-citation><mixed-citation xml:lang="en">Rajpurkar, P., Zhang, J., Lopyrev, K. &amp; Liang, P. (2016). SQuAD: 100,000+ Questions for Machine Comprehension of Text. In: Proceedings of the 2016 Conference on Empirical Methods in Natural Language Processing. Austin, Texas: Association for Computational Linguistics, pp. 2383–2392. DOI: 10.18653/v1/D16-1264.</mixed-citation></citation-alternatives></ref><ref id="cit8"><label>8</label><citation-alternatives><mixed-citation xml:lang="ru">Rajpurkar P., Jia R., Liang P. Know What You Don’t Know: Unanswerable Questions for SQuAD C// Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics. Volume 2: Short Papers. Melbourne, Australia: Association for Computational Linguistics, 2018. P. 784–789. DOI: 10.18653/v1/P18-2124.</mixed-citation><mixed-citation xml:lang="en">Rajpurkar, P., Jia, R. &amp; Liang, P. (2018). Know What You Don’t Know: Unanswerable Questions for SQuAD C. In: Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics. Volume 2: Short Papers. Melbourne, Australia: Association for Computational Linguistics, pp. 784–789. DOI: 10.18653/v1/P18-2124.</mixed-citation></citation-alternatives></ref><ref id="cit9"><label>9</label><citation-alternatives><mixed-citation xml:lang="ru">Gao J., Galley M., Li L. Neural Approaches to Conversational AI: Question Answering, Task-Oriented Dialogues and Social Chatbots // Foundations and Trends® in Information Retrieval. 2019. Vol. 13. No. 2-3. P. 127–298. DOI: 10.1561/1500000074.</mixed-citation><mixed-citation xml:lang="en">Gao, J., Galley, M. &amp; Li, L. (2019). Neural Approaches to Conversational AI: Question Answering, Task-Oriented Dialogues and Social Chatbots. In: Foundations and Trends® in Information Retrieval, 13 (2-3), 127–298. DOI: 10.1561/1500000074.</mixed-citation></citation-alternatives></ref><ref id="cit10"><label>10</label><citation-alternatives><mixed-citation xml:lang="ru">Hewitt J., Manning P. D. A Structural Probe for Finding Syntax in Word Representations // Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies. Volume 1. Long and Short Papers. Minneapolis, Minnesota: Association for Computational Linguistics, 2019. P. 4129–4138. DOI: 10.18653/v1/N19-1419.</mixed-citation><mixed-citation xml:lang="en">Hewitt, J. &amp; Manning, P. D. (2019). A Structural Probe for Finding Syntax in Word Representations. In: Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies. Volume 1. Long and Short Papers. Minneapolis, Minnesota: Association for Computational Linguistics, pp. 4129–4138. DOI: 10.18653/v1/N19-1419.</mixed-citation></citation-alternatives></ref><ref id="cit11"><label>11</label><citation-alternatives><mixed-citation xml:lang="ru">Chi E. A., Hewitt J., Manning P. D. Finding Universal Grammatical Relations in Multilingual BERT [Электронный ресурс] // Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics. 2020. URL: https://aclanthology.org/2020.acl-main.493.pdf (дата обращения: 13.09.2023). DOI: 10.18653/v1/2020.acl-main.493.</mixed-citation><mixed-citation xml:lang="en">Chi, E. A., Hewitt, J. &amp; Manning, P. D. (2020). Finding Universal Grammatical Relations in Multilingual BERT. In: Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics. URL: https://aclanthology.org/2020.acl-main.493.pdf (accessed: 13.09.2023). DOI: 10.18653/v1/2020.acl-main.493.</mixed-citation></citation-alternatives></ref><ref id="cit12"><label>12</label><citation-alternatives><mixed-citation xml:lang="ru">Максименко О. И. Информационно-поисковые системы: оценка методом нечёткой логики // Вестник Московского государственного областного университета. Серия: Лингвистика. 2014. № 5. С. 45–52.</mixed-citation><mixed-citation xml:lang="en">Maksimenko, O. I. (2014). Information retrieval systems: estimation by fuzzy logic. In: Bulletin of the Moscow Region State University. Series: Linguistics, 5, 45–52 (in Russ.).</mixed-citation></citation-alternatives></ref><ref id="cit13"><label>13</label><citation-alternatives><mixed-citation xml:lang="ru">Shwartz S. Artificial Intelligence 101 [Электронный ресурс] // AI Perspectives: [сайт]. URL: https://www.aiperspectives.com/artificial-intelligence-101 (дата обращения: 15.09.2023).</mixed-citation><mixed-citation xml:lang="en">Shwartz S. Artificial Intelligence 101. In: AI Perspectives. URL: https://www.aiperspectives.com/artificial-intelligence-101/ (accessed: 15.09.2023).</mixed-citation></citation-alternatives></ref><ref id="cit14"><label>14</label><citation-alternatives><mixed-citation xml:lang="ru">Attention is All You Need / A. Vaswani, N. Shazeer, N. Parmar, J. Uszkoreit, J. Llion, A. N. Gomez, L. Kaiser, I. Polosukhin // NIPS'17: Proceedings of the 31st International Conference on Neural Information Processing Systems. Red Hook, New York: Curran Associates Inc., 2017. P. 6000–6010. DOI: 10.5555/3295222.3295349.</mixed-citation><mixed-citation xml:lang="en">Vaswani, A., Shazeer, N., Parmar, N., Uszkoreit, J., Llion, J., Gomez, A. N., Kaiser, L. &amp; Polosukhin, I. (2017). Attention is All You Need. In: NIPS'17: Proceedings of the 31st International Conference on Neural Information Processing Systems. Red Hook, New York: Curran Associates Inc., pp. 6000–6010. DOI: 10.5555/3295222.3295349.</mixed-citation></citation-alternatives></ref><ref id="cit15"><label>15</label><citation-alternatives><mixed-citation xml:lang="ru">Unsupervised Cross-Lingual Representation Learning at Scale [Электронный ресурс] / A. Conneau, K. Khandelwal, N. Goyal, V. Chaudhary, G. Wenzek, F. Guzmán, E. Grave, M. Ott, L. Zettlemoyer, V. Stoyanov // Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics. 2020. URL: https://aclanthology.org/2020.acl-main.747.pdf (дата обращения: 15.09.2023). DOI: 10.18653/v1/2020.acl-main.747.</mixed-citation><mixed-citation xml:lang="en">Conneau, A., Khandelwal, K., Goyal, N., Chaudhary, V., Wenzek, G., Guzmán, F., Grave, E., Ott, M., Zettlemoyer, L. &amp; Stoyanov, V. (2020). Unsupervised Cross-Lingual Representation Learning at Scale. In: Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics. URL: https://aclanthology.org/2020.acl-main.747.pdf (accessed: 15.09.2023). DOI: 10.18653/v1/2020.acl-main.747.</mixed-citation></citation-alternatives></ref><ref id="cit16"><label>16</label><citation-alternatives><mixed-citation xml:lang="ru">Sousa N., Oliveira N., Praça I. Machine Reading at Scale: A Search Engine for Scientific and Academic Research //Systems. 2022. Vol. 10. No. 2. Article 43. DOI: 10.3390/systems10020043.</mixed-citation><mixed-citation xml:lang="en">Sousa, N., Oliveira, N. &amp; Praça I. (2022). Machine Reading at Scale: A Search Engine for Scientific and Academic Research. In: Systems, 10 (2), 43. DOI: 10.3390/systems10020043.</mixed-citation></citation-alternatives></ref><ref id="cit17"><label>17</label><citation-alternatives><mixed-citation xml:lang="ru">Manning C. D., Raghavan P., Schütze H. An Introduction to Information Retrieval. Cambridge: Cambridge University Press, 2009. 506 p.</mixed-citation><mixed-citation xml:lang="en">Manning, C. D., Raghavan, P. &amp; Schütze, H. (2009). An Introduction to Information Retrieval. Cambridge: Cambridge University Press.</mixed-citation></citation-alternatives></ref><ref id="cit18"><label>18</label><citation-alternatives><mixed-citation xml:lang="ru">Language Models are Few-Shot Learners / T. Brown, B. Mann, N. Ryder, M. Subbiah, J. D. Kaplan, et al. // NIPS'20: Proceedings of the 34th International Conference on Neural Information Processing Systems. Red Hook, New York: Curran Associates Inc., 2020. P. 1877–1901. DOI: 10.48550/arXiv.2005.14165.</mixed-citation><mixed-citation xml:lang="en">Brown, T., Mann, B., Ryder, N., Subbiah, M., Kaplan, J. D. et al. (2020). Language Models are Few-Shot Learners. In: NIPS'20: Proceedings of the 34th International Conference on Neural Information Processing Systems. Red Hook, New York: Curran Associates Inc., pp. 1877–1901. DOI: 10.48550/arXiv.2005.14165.</mixed-citation></citation-alternatives></ref><ref id="cit19"><label>19</label><citation-alternatives><mixed-citation xml:lang="ru">Клепальченко И. А. Использование теории лексико-семантического поля в качестве основы для представления декларативных знаний // Вестник Московского государственного областного университета. Серия: Лингвистика. 2018. № 1. С. 18–24. DOI: 10.18384/2310-712X-2018-1-18-24.</mixed-citation><mixed-citation xml:lang="en">Klepalchenko, I. A. (2018). The Theory of Semantic Field as a Basis for the Declarative Knowledge Representation. In: Bulletin of Moscow Region State University. Series: Linguistics, 1, 18–24 (in Russ.). DOI: 10.18384/2310-712X-2018-1-18-24 (in Russ.).</mixed-citation></citation-alternatives></ref></ref-list><fn-group><fn fn-type="conflict"><p>The authors declare that there are no conflicts of interest present.</p></fn></fn-group></back></article>
