Вестник Волгоградского государственного университета. Серия 2. Языкознание1998-99112409-197910.15688/jvolsu2.2024.5.4Автоматизированное резюмирование: от методов извлечения к абстрактному обобщениюExploring Automated Summarization: From Extraction to AbstractionСорокинаСветлана ГеннадьевнаСорокинаСветлана ГеннадьевнаSorokinaSvetlanalana40ina@mail.ru0000-0002-8667-6743I.M. Sechenov First Moscow State Medical University (Moscow, Russian Federation)Первый Московский государственный медицинский университет им. И.М. Сеченова (Сеченовский университет) (Москва, Российская Федерация)2712202423547592803202420082024CC BY 4.0

В статье представлен обзор моделей автоматизированного резюмирования текста, основанных на технологиях искусственного интеллекта и использующих два основных подхода: экстрактивный (извлекающий) и абстрактивный (обобщающий). Цель исследования заключается в оценке компрессионных возможностей этих моделей и их языковой компетентности. Степень сжатия оценивается при помощи количественных показателей: количество страниц, слов и символов. Для оценки языковой компетентности принимается во внимание способность моделей применять разнообразные грамматические и лексические конструкции без искажения смысла и содержания. Для оценки потенциала автоматизированного резюмирования были выбраны модели OpenAI Summate.it, WordTune, SciSummary, Scholarcy и OpenAI ChatGPT-4, материалом для анализа послужили тексты публикаций по разным научным дисциплинам. Результаты позволили установить, что выбранные модели с опорой на гибридную стратегию интегрируют как экстрактивные, так и абстрактивные технологии. Тексты, созданные этими инструментами, варьировались по степени полноты и точности, при этом степень сжатия страниц составила от 50 до 95 %, а сокращение количества символов достигло 98 %. Качественная оценка показала, что, хотя модели в целом обладают способностью точно передавать основные идеи исходных текстов, некоторые резюме отличаются излишним упрощением или неверными смысловыми акцентами. Несмотря на эти ограничения, модели автоматического резюмирования обладают значительным потенциалом не только как инструменты для сжатия текста, но и как генераторы нового контента, который может стать ценным объектом для лингвистического анализа, способствуя изучению процессов машинного порождения языка и смысловой переработки текстов.

This paper provides a review of AI-powered automated summarization models, with a focus on two principal approaches: extractive and abstractive. The study aims to evaluate the capabilities of these models in generating concise yet meaningful summaries and analyze their lexical proficiency and linguistic fluidity. The compression rates are assessed using quantitative metrics such as page, word, and character counts, while language fluency is described in terms of ability to manipulate grammar and lexical patterns without compromising meaning and content. The study draws on a selection of scientific publications across various disciplines, testing the functionality and output quality of automated summarization tools such as Summate.it, WordTune, SciSummary, Scholarcy, and OpenAI ChatGPT-4. The findings reveal that the selected models employ a hybrid strategy, integrating both extractive and abstractive techniques. Summaries produced by these tools exhibited varying degrees of completeness and accuracy, with page compression rates ranging from 50 to 95%, and character count reductions reaching up to 98%. Qualitative evaluation indicated that while the models generally captured the main ideas of the source texts, some summaries suffered from oversimplification or misplaced emphasis. Despite these limitations, automated summarization models exhibit significant potential as effective tools for both text compression and content generation, highlighting the need for continued research, particularly from the perspective of linguistic analysis. Summaries generated by AI models offer new opportunities for analyzing machine-generated language and provide valuable data for studying how algorithms process, condense, and restructure human language.

автоматизированное резюмированиеэкстрактивное резюмированиеабстрактивное резюмированиеискусственный интеллектнейронные сетимеждисциплинарные исследованияautomated summarizationextractive summarizationabstractive summarizationartificial intelligenceneural networksinterdisciplinary researchArana-Catania M., Procter R., He Y., Liakata M., 2021. Evaluation of Abstractive Summarisation Models with Machine Translation in Deliberative Processes. ArXiv (Cornell University). DOI: https://doi.org/10.48550/arxiv.2110.05847Bawden D., Robinson L. 2020. Information Overload: An Overview. Oxford Encyclopedia of Political Decision Making. Oxford, Oxford University Press. DOI: 10.1093/acrefore/9780190228637. 013.1360Belwal R.C., Rai S., Gupta A., 2021. A New Graph-Based Extractive Text Summarization Using Keywords or Topic Modeling. Journal of Ambient Intelligence and Humanized Computing, vol. 12, no. 10, pp. 8975-8990. DOI: https://doi.org/10.1007/s12652-020-02591-xBhargava R., Sharma Y., 2020. Deep Extractive Text Summarization. Procedia Computer Science, no. 167, pp. 138-146. DOI: https://doi.org/10.1016/j.procs.2020.03.191Collins E., Augenstein I., Riedel S., 2017. A Supervised Approach to Extractive Summarisation of Scientific Papers.  Proceedings of the 21st Conference on Computational Natural Language Learning (CoNLL 2017). Association for Computational Linguistics, pp. 195-205. DOI: https://doi.org/10.18653/v1/K17-1021Gehrmann S., Deng Y., Rush A., 2018. Bottom-Up Abstractive Summarization. Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing. DOI: https://doi.org/10.18653/v1/d18-1443Gooch P., Warren-Jones E., 2020. A Study’s Got to Know Its Limitations. DOI: 10.1101/2020.04.29.067843.Gupta S., Gupta S.K., 2019. Abstractive Summarization: An Overview of the State of the Art. Expert Systems with Applications, no. 121, pp. 49-65. DOI: https://doi.org/10.1016/j.eswa.2018.12.011Khan A., Salim N., Jaya Kumar Y., 2015. A Framework for Multi-Document Abstractive Summarization Based on Semantic Role Labelling. Applied Soft Computing, no. 30, pp. 737-747. DOI: https://doi.org/10.1016/j.asoc.2015.01.070Lamsiyah S., El Mahdaouy A., El Alaoui S.O., Espinasse B., 2020. A Supervised Method for Extractive Single Document Summarization Based on Sentence Embeddings and Neural Networks. Advances in Intelligent Systems and Computing, vol. 1105, pp. 75-88. DOI: https://doi.org/10.1007/978-3-030-36674-2_8Mishra A.R., Naruka M.S., Tiwari S., 2023. Extraction Techniques and Evaluation Measures for Extractive Text Summarisation. Sustainable Computing: Transforming Industry 4.0 to Society. Springer EBooks, pp. 279-290. DOI: https://doi.org/10.1007/978-3-031-13577-4_17Mohan M.J., Sunitha C., Ganesh A., Jaya A., 2016. A Study on Ontology Based Abstractive Summarization. Procedia Computer Science, no. 87, pp. 32-37. DOI: https://doi.org/10.1016/j.procs.2016.05.122Orasan C., Pekar V., Hasler, L., 2004. A Comparison of Summarisation Methods Based on Term Specificity Estimation. Proceedings of the Fourth International Conference on Language Resources and Evaluation (LREC’04). Lisbon, European Language Resources Association (ELRA), pp. 1037-1040.Polyakova I.N., Zaitsev I.O., 2022. Modification of the Graph Method for Automatic Summarization Tasks Taking into Account Synonymy. International Journal of Open Information Technologies, vol. 10, no. 4, pp. 45-54.Puduppully R.S., Jain P., Chen N., Steedman M., 2023. Multi-Document Summarization with Centroid-Based Pretraining. Edinburgh Research Explorer (University of Edinburgh). DOI: https://doi.org/10.18653/v1/2023.acl-short.13Sorokina S.G., 2016. Ispolzovaniye rekurentnosti kak sredstva argumentatsii pri postroyenii tekstov nauchnogo soderzhaniya: dis. ... kand. filol. nauk [Use of Recurrence as a Means of Argumentation in the Construction of Texts of Scientific Content. Cand. philol. sci. diss.]. Moscow. 196 p.Sorokina S.G., 2023. Iskusstvennyy intellekt v kontekste mezhdistsiplinarnykh issledovaniy yazyka [Artificial Intelligence in Interdisciplinary Linguistics]. Vestnik Kemerovskogo gosudarstvennogo universiteta. Seriya: Gumanitarnye i obshchestvennye nauki [Bulletin of Kemerovo State University. Series: Humanities and Social Science], vol. 7, no. 3, pp. 267-280. DOI: https://doi. org/10.21603/2542-1840-2023-7-3-267-280Sorokina S.G., 2024. Osobennosti primeneniya tekhnologii avtomaticheskoy summarizatsii k nauchnym publikatsiyam [Applying Automatic Summarization Technology to Academic Publications]. Tri «l» v paradigme sovremennogo gumanitarnogo znaniya: lingvistika, literaturovedenie, lingvodidaktika: sb. nauch. st. [Three L’s in the Paradigm of Modern Humanitarian Knowledge: Linguistics, Literary Criticism, Linguodidactics. Collection of Scientific Articles]. Moscow, Yaz. narodov mira Publ., pp. 132-138.Sorokina S.G., Ulanova K.L., 2020. Implementatsiya kategorii tozhdestva v nazvaniyakh publitsisticheskikh i nauchnykh tekstov [Role of Article Title in Implementing the Category of Identity]. Sovremennoe pedagogicheskoe obrazovanie [Modern Pedagogical Education], no. 2, pp. 202-207.Thaiprayoon S., Unger H., Kubek M., 2021. Graph and Centroid-Based Word Clustering. Proceedings of the 4th International Conference on Natural Language Processing and Information Retrieval, pp. 163-168. DOI: https://doi.org/10.1145/3443279.3443290Vertinova A.A., Pashuk N.R., Makogonova P.V., Kosheleva A.I., 2022. Otsenka vliyaniya informatsionnogo shuma na prinyatiye resheniy [Assessing the Infoglut Impact on Decision-Making]. Liderstvo i menedzhment [Leadership and Management], vol. 9, no. 3, pp. 877-890. DOI: https://doi.org/10.18334/lim.9.3.116218Yadav A.K., Ranvijay N., Yadav R.S., Maurya A.K., 2023. Graph-Based Extractive Text Summarization Based on Single Document. Multimedia Tools and Applications, vol. 83, no. 7, pp. 18987-19013. DOI: https://doi.org/10.1007/s11042-023-16199-8T1 – Sundstrom S.M., Angeler D.G., Ernakovich J.G., Garcнa J., Hamm J.A., Huntington O., Allen C.R. The Emergence of Convergence. Elementa, 2023, vol. 11, no. 1. DOI: https://doi.org/10.1525/elementa.2022.00128T2 – Karunathilake E.M.B.M., Le A.T., Heo S., Chung Y.S., 2023. The Path to Smart Farming: Innovations and Opportunities in Precision Agriculture. Agriculture, vol. 13, no. 8, p. 1593. DOI: https://doi.org/10.3390/agriculture13081593T3 – Maka A.O.M., Alabid J.M. Solar Energy Technology and Its Roles in Sustainable Development. Clean Energy, 2022, vol. 6, no. 3, pp. 476-483. DOI: https://doi.org/10.1093/ce/zkac023T4 – Abdul Malik N., Syafiq Ya Shak M., Mohamad F., Joharry S.A. Corpus-Based Studies of Metaphor: An Overview. Arab World English Journal, 2022, vol. 13, no. 2, pp. 512-528. DOI: https://doi.org/10.24093/awej/vol13no2.36Cambridge Dictionary. URL: https://dictionary.cambridge.org/ru/Oxford English Dictionary. URL: https://www.oed.com/?tl=trueArana-Catania M., Procter R., He Y., Liakata M., 2021. Evaluation of Abstractive Summarisation Models with Machine Translation in Deliberative Processes. ArXiv (Cornell University). DOI: https://doi.org/10.48550/arxiv.2110.05847Bawden D., Robinson L. 2020. Information Overload: An Overview. Oxford Encyclopedia of Political Decision Making. Oxford, Oxford University Press. DOI: 10.1093/acrefore/9780190228637. 013.1360Belwal R.C., Rai S., Gupta A., 2021. A New Graph-Based Extractive Text Summarization Using Keywords or Topic Modeling. Journal of Ambient Intelligence and Humanized Computing, vol. 12, no. 10, pp. 8975-8990. DOI: https://doi.org/10.1007/s12652-020-02591-xBhargava R., Sharma Y., 2020. Deep Extractive Text Summarization. Procedia Computer Science, no. 167, pp. 138-146. DOI: https://doi.org/10.1016/j.procs.2020.03.191Collins E., Augenstein I., Riedel S., 2017. A Supervised Approach to Extractive Summarisation of Scientific Papers.  Proceedings of the 21st Conference on Computational Natural Language Learning (CoNLL 2017). Association for Computational Linguistics, pp. 195-205. DOI: https://doi.org/10.18653/v1/K17-1021Gehrmann S., Deng Y., Rush A., 2018. Bottom-Up Abstractive Summarization. Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing. DOI: https://doi.org/10.18653/v1/d18-1443Gooch P., Warren-Jones E., 2020. A Study’s Got to Know Its Limitations. DOI: 10.1101/2020.04.29.067843.Gupta S., Gupta S.K., 2019. Abstractive Summarization: An Overview of the State of the Art. Expert Systems with Applications, no. 121, pp. 49-65. DOI: https://doi.org/10.1016/j.eswa.2018.12.011Khan A., Salim N., Jaya Kumar Y., 2015. A Framework for Multi-Document Abstractive Summarization Based on Semantic Role Labelling. Applied Soft Computing, no. 30, pp. 737-747. DOI: https://doi.org/10.1016/j.asoc.2015.01.070Lamsiyah S., El Mahdaouy A., El Alaoui S.O., Espinasse B., 2020. A Supervised Method for Extractive Single Document Summarization Based on Sentence Embeddings and Neural Networks. Advances in Intelligent Systems and Computing, vol. 1105, pp. 75-88. DOI: https://doi.org/10.1007/978-3-030-36674-2_8Mishra A.R., Naruka M.S., Tiwari S., 2023. Extraction Techniques and Evaluation Measures for Extractive Text Summarisation. Sustainable Computing: Transforming Industry 4.0 to Society. Springer EBooks, pp. 279-290. DOI: https://doi.org/10.1007/978-3-031-13577-4_17Mohan M.J., Sunitha C., Ganesh A., Jaya A., 2016. A Study on Ontology Based Abstractive Summarization. Procedia Computer Science, no. 87, pp. 32-37. DOI: https://doi.org/10.1016/j.procs.2016.05.122Orasan C., Pekar V., Hasler, L., 2004. A Comparison of Summarisation Methods Based on Term Specificity Estimation. Proceedings of the Fourth International Conference on Language Resources and Evaluation (LREC’04). Lisbon, European Language Resources Association (ELRA), pp. 1037-1040.Polyakova I.N., Zaitsev I.O., 2022. Modification of the Graph Method for Automatic Summarization Tasks Taking into Account Synonymy. International Journal of Open Information Technologies, vol. 10, no. 4, pp. 45-54.Puduppully R.S., Jain P., Chen N., Steedman M., 2023. Multi-Document Summarization with Centroid-Based Pretraining. Edinburgh Research Explorer (University of Edinburgh). DOI: https://doi.org/10.18653/v1/2023.acl-short.13Sorokina S.G., 2016. Ispolzovaniye rekurentnosti kak sredstva argumentatsii pri postroyenii tekstov nauchnogo soderzhaniya: dis. ... kand. filol. nauk [Use of Recurrence as a Means of Argumentation in the Construction of Texts of Scientific Content. Cand. philol. sci. diss.]. Moscow. 196 p.Sorokina S.G., 2023. Iskusstvennyy intellekt v kontekste mezhdistsiplinarnykh issledovaniy yazyka [Artificial Intelligence in Interdisciplinary Linguistics]. Vestnik Kemerovskogo gosudarstvennogo universiteta. Seriya: Gumanitarnye i obshchestvennye nauki [Bulletin of Kemerovo State University. Series: Humanities and Social Science], vol. 7, no. 3, pp. 267-280. DOI: https://doi. org/10.21603/2542-1840-2023-7-3-267-280Sorokina S.G., 2024. Osobennosti primeneniya tekhnologii avtomaticheskoy summarizatsii k nauchnym publikatsiyam [Applying Automatic Summarization Technology to Academic Publications]. Tri «l» v paradigme sovremennogo gumanitarnogo znaniya: lingvistika, literaturovedenie, lingvodidaktika: sb. nauch. st. [Three L’s in the Paradigm of Modern Humanitarian Knowledge: Linguistics, Literary Criticism, Linguodidactics. Collection of Scientific Articles]. Moscow, Yaz. narodov mira Publ., pp. 132-138.Sorokina S.G., Ulanova K.L., 2020. Implementatsiya kategorii tozhdestva v nazvaniyakh publitsisticheskikh i nauchnykh tekstov [Role of Article Title in Implementing the Category of Identity]. Sovremennoe pedagogicheskoe obrazovanie [Modern Pedagogical Education], no. 2, pp. 202-207.Thaiprayoon S., Unger H., Kubek M., 2021. Graph and Centroid-Based Word Clustering. Proceedings of the 4th International Conference on Natural Language Processing and Information Retrieval, pp. 163-168. DOI: https://doi.org/10.1145/3443279.3443290Vertinova A.A., Pashuk N.R., Makogonova P.V., Kosheleva A.I., 2022. Otsenka vliyaniya informatsionnogo shuma na prinyatiye resheniy [Assessing the Infoglut Impact on Decision-Making]. Liderstvo i menedzhment [Leadership and Management], vol. 9, no. 3, pp. 877-890. DOI: https://doi.org/10.18334/lim.9.3.116218Yadav A.K., Ranvijay N., Yadav R.S., Maurya A.K., 2023. Graph-Based Extractive Text Summarization Based on Single Document. Multimedia Tools and Applications, vol. 83, no. 7, pp. 18987-19013. DOI: https://doi.org/10.1007/s11042-023-16199-8T1 – Sundstrom S.M., Angeler D.G., Ernakovich J.G., Garcнa J., Hamm J.A., Huntington O., Allen C.R. The Emergence of Convergence. Elementa, 2023, vol. 11, no. 1. DOI: https://doi.org/10.1525/elementa.2022.00128T2 – Karunathilake E.M.B.M., Le A.T., Heo S., Chung Y.S., 2023. The Path to Smart Farming: Innovations and Opportunities in Precision Agriculture. Agriculture, vol. 13, no. 8, p. 1593. DOI: https://doi.org/10.3390/agriculture13081593T3 – Maka A.O.M., Alabid J.M. Solar Energy Technology and Its Roles in Sustainable Development. Clean Energy, 2022, vol. 6, no. 3, pp. 476-483. DOI: https://doi.org/10.1093/ce/zkac023T4 – Abdul Malik N., Syafiq Ya Shak M., Mohamad F., Joharry S.A. Corpus-Based Studies of Metaphor: An Overview. Arab World English Journal, 2022, vol. 13, no. 2, pp. 512-528. DOI: https://doi.org/10.24093/awej/vol13no2.36Cambridge Dictionary. URL: https://dictionary.cambridge.org/ru/Oxford English Dictionary. URL: https://www.oed.com/?tl=true