<?xml version="1.0" encoding="UTF-8"?>
<article article-type="research-article" dtd-version="1.3" xml:lang="ru" xmlns:xlink="http://www.w3.org/1999/xlink" xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance" xsi:noNamespaceSchemaLocation="https://metafora.rcsi.science/xsd_files/journal3.xsd">
  <front>
    <journal-meta>
      <journal-id journal-id-type="publisher-id">moitvivt</journal-id>
      <journal-title-group>
        <journal-title xml:lang="ru">Моделирование, оптимизация и информационные технологии</journal-title>
        <trans-title-group xml:lang="en">
          <trans-title>Modeling, Optimization and Information Technology</trans-title>
        </trans-title-group>
      </journal-title-group>
      <issn pub-type="epub">2310-6018</issn>
      <publisher>
        <publisher-name>Издательство</publisher-name>
      </publisher>
    </journal-meta>
    <article-meta>
      <article-id pub-id-type="doi">10.26102/2310-6018/2026.54.3.013</article-id>
      <article-id pub-id-type="custom" custom-type="elpub">2220</article-id>
      <title-group>
        <article-title xml:lang="ru">Гибридная семантическая редукция текстов в библиотечных информационных системах</article-title>
        <trans-title-group xml:lang="en">
          <trans-title>Hybrid semantic reduction of texts in library information systems</trans-title>
        </trans-title-group>
      </title-group>
      <contrib-group>
        <contrib contrib-type="author">
          <contrib-id contrib-id-type="orcid">0009-0002-1702-591X</contrib-id>
          <name-alternatives>
            <name name-style="eastern" xml:lang="ru">
              <surname>Рзянкин</surname>
              <given-names>Илья Сергеевич</given-names>
            </name>
            <name name-style="western" xml:lang="en">
              <surname>Rzyankin</surname>
              <given-names>Ilya Sergeevich</given-names>
            </name>
          </name-alternatives>
          <email>i-rzyankin@yandex.ru</email>
          <xref ref-type="aff">aff-1</xref>
        </contrib>
        <contrib contrib-type="author">
          <contrib-id contrib-id-type="orcid">0000-0001-8966-3633</contrib-id>
          <name-alternatives>
            <name name-style="eastern" xml:lang="ru">
              <surname>Носков</surname>
              <given-names>Михаил Валерианович</given-names>
            </name>
            <name name-style="western" xml:lang="en">
              <surname>Noskov</surname>
              <given-names>Mikhail Valerianovich</given-names>
            </name>
          </name-alternatives>
          <email>mnoskov@sfu-kras.ru</email>
          <xref ref-type="aff">aff-2</xref>
        </contrib>
      </contrib-group>
      <aff-alternatives id="aff-1">
        <aff xml:lang="ru">Сибирский федеральный университет</aff>
        <aff xml:lang="en">Siberian Federal University</aff>
      </aff-alternatives>
      <aff-alternatives id="aff-2">
        <aff xml:lang="ru">Сибирский федеральный университет</aff>
        <aff xml:lang="en">Siberian Federal University</aff>
      </aff-alternatives>
      <pub-date pub-type="epub">
        <day>01</day>
        <month>01</month>
        <year>2026</year>
      </pub-date>
      <volume>1</volume>
      <issue>1</issue>
      <elocation-id>10.26102/2310-6018/2026.54.3.013</elocation-id>
      <permissions>
        <copyright-statement>Copyright © Авторы, 2026</copyright-statement>
        <copyright-year>2026</copyright-year>
        <license license-type="creative-commons-attribution" xlink:href="https://creativecommons.org/licenses/by/4.0/">
          <license-p>This work is licensed under a Creative Commons Attribution 4.0 International License</license-p>
        </license>
      </permissions>
      <self-uri xlink:href="https://moitvivt.ru/ru/journal/article?id=2220"/>
      <abstract xml:lang="ru">
        <p>Актуальность исследования обусловлена ростом объемов текстовой информации в библиотечных информационных системах и необходимостью обеспечения быстрой и содержательной навигации по электронным фондам в условиях ограниченных вычислительных ресурсов. Существующие решения автоматической суммаризации ориентированы преимущественно на использование крупномасштабных языковых моделей, что затрудняет их внедрение в локальную библиотечную инфраструктуру. В связи с этим работа направлена на разработку ресурсосберегающего метода семантической редукции текста, обеспечивающего баланс между качеством смыслового представления и вычислительной доступностью. Ведущим подходом является гибридная архитектура, основанная на последовательном применении лексической редукции с использованием облаков слов и нейросетевой суммаризации компактными моделями. В исследовании предложена контекстно-ориентированная метрика оценки релевантности, учитывающая семантическую целостность, структурные характеристики и доменно значимые термины библиотечной среды. Экспериментальное исследование на корпусе из 1178 документов показало, что гибридный подход обеспечивает прирост показателей релевантности при одновременном сокращении времени инференса по сравнению с прямой нейросетевой суммаризацией полного текста. Полученные результаты подтверждают возможность практического внедрения предложенного метода в библиотечных информационных системах с ограниченной вычислительной инфраструктурой и его применимость для задач навигации и каталогизации.</p>
      </abstract>
      <trans-abstract xml:lang="en">
        <p>The relevance of the study is determined by the continuous growth of textual information in library information systems and the need to ensure fast and meaningful navigation across electronic collections under constrained computational resources. Existing automatic summarization solutions are primarily oriented toward large-scale language models, which limits their practical deployment within local library infrastructures. In this context, the paper aims to develop a resource-efficient method of semantic text reduction that balances the quality of semantic representation with computational feasibility. The proposed approach is based on a hybrid architecture that sequentially combines lexical reduction using word clouds with neural summarization performed by compact models. In addition, a context-oriented evaluation metric is introduced to assess relevance with regard to semantic coherence, structural characteristics, and domain-specific terms significant for the library environment. An experimental study conducted on a corpus of 1178 documents demonstrates that the hybrid approach improves relevance indicators while simultaneously reducing inference time compared to direct neural summarization of the full text. The obtained results confirm the practical applicability of the proposed method for library information systems operating under limited computational infrastructure and its usefulness for navigation and cataloging tasks.</p>
      </trans-abstract>
      <kwd-group xml:lang="ru">
        <kwd>семантическая редукция текста</kwd>
        <kwd>автоматическая суммаризация</kwd>
        <kwd>облако слов</kwd>
        <kwd>библиотечные информационные системы</kwd>
        <kwd>гибридные методы обработки текста</kwd>
        <kwd>нейросетевые модели</kwd>
        <kwd>оценка релевантности</kwd>
        <kwd>Library Relevance Score</kwd>
      </kwd-group>
      <kwd-group xml:lang="en">
        <kwd>semantic text reduction</kwd>
        <kwd>automatic summarization</kwd>
        <kwd>word cloud</kwd>
        <kwd>library information systems</kwd>
        <kwd>hybrid text processing methods</kwd>
        <kwd>neural models</kwd>
        <kwd>relevance evaluation</kwd>
        <kwd>Library Relevance Score</kwd>
      </kwd-group>
      <funding-group>
        <funding-statement xml:lang="ru">Исследование выполнено без спонсорской поддержки.</funding-statement>
        <funding-statement xml:lang="en">The study was performed without external funding.</funding-statement>
      </funding-group>
    </article-meta>
  </front>
  <back>
    <ref-list>
      <title>References</title>
      <ref id="cit1">
        <label>1</label>
        <mixed-citation xml:lang="ru">Lyon L. The Informatics Transform: Re-Engineering Libraries for the Data Decade. International Journal of Digital Curation. 2012;7(1):126–138. https://doi.org/10.2218/ijdc.v7i1.220</mixed-citation>
      </ref>
      <ref id="cit2">
        <label>2</label>
        <mixed-citation xml:lang="ru">Roy P. Big data analytics in university libraries on today's librarianship decision-making: A disruptive innovation perspective. IFLA Journal. 2025;51(8). https://doi.org/10.1177/03400352251318753</mixed-citation>
      </ref>
      <ref id="cit3">
        <label>3</label>
        <mixed-citation xml:lang="ru">Mridha M.F., Lima A.A., Nur K., et al. A Survey of Automatic Text Summarization: Progress, Process and Challenges. IEEE Access. 2021;9:156043–156070. https://doi.org/10.1109/ACCESS.2021.3129786</mixed-citation>
      </ref>
      <ref id="cit4">
        <label>4</label>
        <mixed-citation xml:lang="ru">Arnaboldi V., Cho J., Sternberg P.W. Wormicloud: A new text summarization tool based on word clouds to explore the C. elegans literature. Database. 2021;2021. https://doi.org/10.1093/database/baab015</mixed-citation>
      </ref>
      <ref id="cit5">
        <label>5</label>
        <mixed-citation xml:lang="ru">Strubell E., Ganesh A., McCallum A. Energy and Policy Considerations for Deep Learning in NLP. In: Proceedings of the 57th Conference of the Association for Computational Linguistics, ACL 2019: Volume 1: Long Papers, 28 July – 02 August 2019, Florence, Italy. Association for Computational Linguistics; 2019. P. 3645–3650. https://doi.org/10.18653/v1/P19-1355</mixed-citation>
      </ref>
      <ref id="cit6">
        <label>6</label>
        <mixed-citation xml:lang="ru">Treviso M., Lee J.-U., Ji T., et al. Efficient Methods for Natural Language Processing: A Survey. Transactions of the Association for Computational Linguistics. 2023;11:826–860. https://doi.org/10.1162/tacl_a_00577</mixed-citation>
      </ref>
      <ref id="cit7">
        <label>7</label>
        <mixed-citation xml:lang="ru">Syed A.A., Gaol F.L., Matsuo T. A Survey of the State-of-the-Art Models in Neural Abstractive Text Summarization. IEEE Access. 2021;9:13248–13265. https://doi.org/10.1109/ACCESS.2021.3052783</mixed-citation>
      </ref>
      <ref id="cit8">
        <label>8</label>
        <mixed-citation xml:lang="ru">Goodwin T., Savery M., Demner-Fushman D. Flight of the PEGASUS? Comparing Transformers on Few-Shot and Zero-Shot Multi-document Abstractive Summarization. In: Proceedings of the 28th International Conference on Computational Linguistics, COLING 2020, 08–13 December 2020, Barcelona, Spain (Online). International Committee on Computational Linguistics; 2020. P. 5640–5646. https://doi.org/10.18653/v1/2020.coling-main.494</mixed-citation>
      </ref>
      <ref id="cit9">
        <label>9</label>
        <mixed-citation xml:lang="ru">Li J. A comparative study of keyword extraction algorithms for English texts. Journal of Intelligent Systems. 2021;30:808–815. https://doi.org/10.1515/jisys-2021-0040</mixed-citation>
      </ref>
      <ref id="cit10">
        <label>10</label>
        <mixed-citation xml:lang="ru">Skeppstedt M., Ahltorp M., Kucher K., Lindström M. From word clouds to Word Rain: Revisiting the classic word cloud to visualize climate change texts. Information Visualization. 2024;23(2). https://doi.org/10.1177/14738716241236188</mixed-citation>
      </ref>
      <ref id="cit11">
        <label>11</label>
        <mixed-citation xml:lang="ru">Bhandari M., Gour P.N., Ashfaq A., Liu P., Neubig G. Re-evaluating Evaluation in Text Summarization. In: Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing, EMNLP 2020, 16–20 November 2020, Online. Association for Computational Linguistics; 2020. P. 9347–9359. https://doi.org/10.18653/v1/2020.emnlp-main.751</mixed-citation>
      </ref>
      <ref id="cit12">
        <label>12</label>
        <mixed-citation xml:lang="ru">Hobson S.P., Dorr B.J., Monz Ch., Schwartz R. Task-based evaluation of text summarization using relevance prediction. Information Processing &amp; Management. 2007;43(6):1482–1499. https://doi.org/10.1016/j.ipm.2007.01.002</mixed-citation>
      </ref>
      <ref id="cit13">
        <label>13</label>
        <mixed-citation xml:lang="ru">Ushio A., Liberatore F., Camacho-Collados J. Back to the Basics: A Quantitative Analysis of Statistical and Graph-Based Term Weighting Schemes for Keyword Extraction. In: Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing, EMNLP 2021, 07–11 November 2021, Virtual Event / Punta Cana, Dominican Republic. Association for Computational Linguistics; 2021. P. 8089–8103. https://doi.org/10.18653/v1/2021.emnlp-main.638</mixed-citation>
      </ref>
      <ref id="cit14">
        <label>14</label>
        <mixed-citation xml:lang="ru">Hearst M.A., Pedersen E., Patil L., et al. An Evaluation of Semantically Grouped Word Cloud Designs. IEEE Transactions on Visualization and Computer Graphics. 2020;26(9):2748–2761. https://doi.org/10.1109/TVCG.2019.2904683</mixed-citation>
      </ref>
      <ref id="cit15">
        <label>15</label>
        <mixed-citation xml:lang="ru">Dice D., Kogan A. Optimizing Inference Performance of Transformers on CPUs. arXiv. URL: https://arxiv.org/abs/2102.06621 [Accessed 19th January 2026].</mixed-citation>
      </ref>
      <ref id="cit16">
        <label>16</label>
        <mixed-citation xml:lang="ru">Xu Y., Xu R., Iter D., et al. InheritSumm: A General, Versatile and Compact Summarizer by Distilling from GPT. In: Findings of the Association for Computational Linguistics: EMNLP 2023, 06–10 December 2023, Singapore. Association for Computational Linguistics; 2023. P. 13879–13892. https://doi.org/10.18653/v1/2023.findings-emnlp.927</mixed-citation>
      </ref>
      <ref id="cit17">
        <label>17</label>
        <mixed-citation xml:lang="ru">Lee J.-U., Puerto H., van Aken B. Surveying (Dis)Parities and Concerns of Compute Hungry NLP Research. arXiv. URL: https://arxiv.org/abs/2306.16900 [Accessed 19th January 2026].</mixed-citation>
      </ref>
      <ref id="cit18">
        <label>18</label>
        <mixed-citation xml:lang="ru">Desai Sh., Xu J., Durrett G. Compressive Summarization with Plausibility and Salience Modeling. In: Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing, EMNLP 2020, 16–20 November 2020, Online. Association for Computational Linguistics; 2020. P. 6259–6274. https://doi.org/10.18653/v1/2020.emnlp-main.507</mixed-citation>
      </ref>
      <ref id="cit19">
        <label>19</label>
        <mixed-citation xml:lang="ru">Mei A., Kabir A., Bapat R., et al. Learning to Prioritize: Precision-Driven Sentence Filtering for Long Text Summarization. In: Proceedings of the Thirteenth Language Resources and Evaluation Conference, LREC 2022, 20–25 June 2022, Marseille, France. European Language Resources Association; 2022. P. 313–318.</mixed-citation>
      </ref>
      <ref id="cit20">
        <label>20</label>
        <mixed-citation xml:lang="ru">Liang X., Li J., Wu Sh., et al. An Efficient Coarse-to-Fine Facet-Aware Unsupervised Summarization Framework Based on Semantic Blocks. In: Proceedings of the 29th International Conference on Computational Linguistics, COLING 2022, 12–17 October 2022, Gyeongju, Republic of Korea. International Committee on Computational Linguistics; 2022. P. 6415–6425.</mixed-citation>
      </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>