<?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">scidial</journal-id><journal-title-group><journal-title xml:lang="ru">Научный диалог</journal-title><trans-title-group xml:lang="en"><trans-title>Nauchnyi dialog</trans-title></trans-title-group></journal-title-group><issn pub-type="ppub">2225-756X</issn><issn pub-type="epub">2227-1295</issn><publisher><publisher-name>Limited Liability Company "Center for Scientific and Educational Projects" (CSEP)</publisher-name></publisher></journal-meta><article-meta><article-id pub-id-type="doi">10.24224/2227-1295-2023-12-7-47-65</article-id><article-id custom-type="elpub" pub-id-type="custom">scidial-4797</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>ЯЗЫКОЗНАНИЕ</subject></subj-group><subj-group subj-group-type="section-heading" xml:lang="en"><subject>LINGUISTICS</subject></subj-group></article-categories><title-group><article-title>Типовые различия  естественных и  сгенерированных  нейронной сетью текстов в квантитативном аспекте</article-title><trans-title-group xml:lang="en"><trans-title>Typological Differences  of Natural and Neural  Network-Generated Texts  in a Quantitative 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/0000-0001-9130-2941</contrib-id><name-alternatives><name name-style="eastern" xml:lang="ru"><surname>Тельпов</surname><given-names>Р. Е.</given-names></name><name name-style="western" xml:lang="en"><surname>Telpov</surname><given-names>R. E.</given-names></name></name-alternatives><bio xml:lang="ru"><p>Тельпов Роман Евгеньевич, кандидат филологических наук, доцент кафедры общего и русского языкознания</p><p>Москва</p></bio><bio xml:lang="en"><p>Roman E. Telpov, PhD in Philology, Associate Professor, Department of General and Russian Linguistics</p><p>Moscow</p></bio><email xlink:type="simple">roman-tel-pov@yandex.ru</email><xref ref-type="aff" rid="aff-1"/></contrib><contrib contrib-type="author" corresp="yes"><contrib-id contrib-id-type="orcid">https://orcid.org/0009-0008-8347-9710</contrib-id><name-alternatives><name name-style="eastern" xml:lang="ru"><surname>Ларцина</surname><given-names>С. В.</given-names></name><name name-style="western" xml:lang="en"><surname>Lartsina</surname><given-names>S. V.</given-names></name></name-alternatives><bio xml:lang="ru"><p>Ларцина Станислава Витальевна, магистрант, кафедра общего и русского языкознания</p><p>Москва</p></bio><bio xml:lang="en"><p>Stanislava V. Lartsina, Master’s degree student, Department of General and Russian Linguistics</p><p>Moscow</p></bio><email xlink:type="simple">stasya-200@list.ru</email><xref ref-type="aff" rid="aff-1"/></contrib></contrib-group><aff-alternatives id="aff-1"><aff xml:lang="ru"><institution>Государственный институт русского языка им. А. С. Пушкина</institution><country>Россия</country></aff><aff xml:lang="en"><institution>Pushkin State Russian Language Institute</institution><country>Russian Federation</country></aff></aff-alternatives><pub-date pub-type="collection"><year>2023</year></pub-date><pub-date pub-type="epub"><day>05</day><month>10</month><year>2023</year></pub-date><volume>12</volume><issue>7</issue><fpage>47</fpage><lpage>65</lpage><permissions><copyright-statement>Copyright &amp;#x00A9; Тельпов Р.Е., Ларцина С.В., 2023</copyright-statement><copyright-year>2023</copyright-year><copyright-holder xml:lang="ru">Тельпов Р.Е., Ларцина С.В.</copyright-holder><copyright-holder xml:lang="en">Telpov R.E., Lartsina S.V.</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.nauka-dialog.ru/jour/article/view/4797">https://www.nauka-dialog.ru/jour/article/view/4797</self-uri><abstract><p>Авторы статьи выявляют отличительные черты в текстах, написанных людьми, и в текстах, созданных нейросетью GPT-3. Тексты, сгенерированные GPT-3, еще не становились предметом систематического углубленного изучения. Рассмотрено 160 текстов, распределенных по четырем темам («Высшее образование в моих глазах», «Как оставаться человеком в нечеловеческих условиях?», «Как я провёл лето?», «Педагог года»), 80 из которых созданы нейросетью, а 80 — людьми. Тексты проанализированы с использованием методов квантитативной лингвистики. К каждому из текстов при помощи программы AntConc составлен конкорданс, из которого были получены количественные значения, используемые для дальнейшего анализа. Сделаны следующие выводы: (1) в сгенерированных текстах слова, включённые в заголовок, встречаются с наибольшей частотностью; (2) относительная частота употребления слов, включённых в заголовок, нецелесообразно завышена; (3) в список 20-ти самых частотных слов во всех сгенерированных текстах входит наибольшее количество полнозначных слов; (4) коэффициент лексического разнообразия в естественных текстах значительно выше, нежели у сгенерированных. Результаты исследования могут быть полезны как преподавателям, так и специалистам в области машинного обучения.</p></abstract><trans-abstract xml:lang="en"><p>The authors of this article identify distinctive features in texts written by humans and texts generated by the GPT-3 neural network. Texts generated by GPT-3 have not yet been subject to systematic in-depth study. In total, 160 texts were analyzed in the article, distributed across four topics (“Higher Education in My Eyes,” “How to Remain Human in Inhuman Conditions,” “How I Spent the Summer,” “Teacher of the Year”), with 80 texts generated by the neural network and 80 texts written by humans. The texts were analyzed using quantitative linguistic methods. A concordance was compiled for each text using the AntConc program, from which quantitative values were obtained for further analysis. The authors reached the following conclusions: (1) in the generated texts, words included in the title occur with the highest frequency; (2) the relative frequency of words included in the title is unreasonably inflated; (3) the list of the 20 most frequent words in all generated texts includes the highest number of full-fledged words; (4) the lexical diversity coefficient in the examined natural texts is significantly higher than that of the generated texts. The findings of this research can be useful for both educators and machine learning specialists. </p></trans-abstract><kwd-group xml:lang="ru"><kwd>искусственный интеллект</kwd><kwd>чат-бот</kwd><kwd>нейросеть</kwd><kwd>квантитативная лингвистика</kwd><kwd>сгенерированный текст</kwd><kwd>лемма</kwd><kwd>конкор-данс</kwd><kwd>коэффициент лексического разнообразия</kwd></kwd-group><kwd-group xml:lang="en"><kwd>artificial intelligence</kwd><kwd>chatbot</kwd><kwd>neural network</kwd><kwd>quantitative linguistics</kwd><kwd>generated text</kwd><kwd>lem-ma</kwd><kwd>concordance</kwd><kwd>lexical diversity coefficient</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">Борунов, А. Б. Разнообразие речи и методы его измерения в тексте (лингвостатистический подход) / А. Б. Борунов // Litera. — 2017. — № 4. — С. 81—86.</mixed-citation><mixed-citation xml:lang="en">Borunov, A. B. (2017). Diversity of speech and methods of measuring it in text (linguostatistical approach). Litera, 4: 81—86. (In Russ.).</mixed-citation></citation-alternatives></ref><ref id="cit2"><label>2</label><citation-alternatives><mixed-citation xml:lang="ru">Бурнашев Р. Ф. Роль нейронных сетей в лингвистических исследованиях / Р. Ф Бурнашев, А. С. Аламова // Science and Education. — 2023. — № 3. — С. 258—269.</mixed-citation><mixed-citation xml:lang="en">Burnashev, R. F., Alamova, A. S. (2022). Quantitative linguistics and artificial intelligence. Science and Education, 3(2): 1390—1402. (In Russ.).</mixed-citation></citation-alternatives></ref><ref id="cit3"><label>3</label><citation-alternatives><mixed-citation xml:lang="ru">Бурнашев Р. Ф. Квантитативная лингвистика и искусственный интеллект / Р. Ф. Бурнашев, А. С. Аламова // Science and Education. — 2022. — Т. 3, № 2. — С. 1390—1402.</mixed-citation><mixed-citation xml:lang="en">Burnashev, R. F., Alamova, A. S. (2023). The role of neural networks in linguistic research. Science and Education, 3: 258—269. (In Russ.).</mixed-citation></citation-alternatives></ref><ref id="cit4"><label>4</label><citation-alternatives><mixed-citation xml:lang="ru">Галушкин А. И. Нейронные сети [Электронный ресурс] / А. И. Галушкин // Большая российская энциклопедия. — 2022. — 16 ноября. — Режим доступа : https://old.bigenc.ru/technology_and_technique/text/4114009 (дата обращения: 20.06.2023).</mixed-citation><mixed-citation xml:lang="en">Cohen, A., Mantegna, R., Havlin, S. (2011). Numerical Analysis of Word Frequencies in Artificial and Natural Language Texts. Fractals, 5 (1): 1—19. DOI: 10.1142/S0218348X97000103.</mixed-citation></citation-alternatives></ref><ref id="cit5"><label>5</label><citation-alternatives><mixed-citation xml:lang="ru">Головин Б. Н. Язык и статистика / Б. Н. Головин. — Москва : Просвещение, 1971. — 190 с.</mixed-citation><mixed-citation xml:lang="en">Dale, R. (2021). GPT-3: What’s it good for? Natural Language Engineering, 27 (1): 113— 118. DOI: 10.1017/S1351324920000601.</mixed-citation></citation-alternatives></ref><ref id="cit6"><label>6</label><citation-alternatives><mixed-citation xml:lang="ru">Захарова Е. Ю. Лексическое разнообразие текста и способы его измерения / Е. Ю. Захарова, О. Ю. Савина // Вестник Тюменского государственного университета. Гуманитарные исследования. Humanitates. — 2020. — Т. 6, № 1 (21). — С. 20—34. — DOI: 10.21684/2411-197X-2020-6-1-20-34.</mixed-citation><mixed-citation xml:lang="en">Dinesh, K., Nathan, S. (2023). Study and Analysis of Chat GPT and its Impact on Different Fields of Study. International Journal of Innovative Science and Research Technology (IJISRT), 8 (3): 827—833. DOI: 10.5281/zenodo.7767675.</mixed-citation></citation-alternatives></ref><ref id="cit7"><label>7</label><citation-alternatives><mixed-citation xml:lang="ru">Насырова Г. Н. Обзор современных сервисов и программного обеспечения квантитативной лингвистики / Г. Н. Насырова, Ш. Х. Амонова, Р. Ф. Бурнашев // Science and Education. — 2022. — Т. 3, №. 12. — С. 450—462.</mixed-citation><mixed-citation xml:lang="en">Floridi, L., Chiriatt, M. (2020). GPT-3: Its Nature, Scope, Limits, and Consequences. Minds and Machines, 30 (2): 1—14. DOI: 10.1007/s11023-020-09548-1.</mixed-citation></citation-alternatives></ref><ref id="cit8"><label>8</label><citation-alternatives><mixed-citation xml:lang="ru">«Речевое творчество» искусственного интеллекта : какие тексты пишет машина и чем они отличаются от людских / А. Ю. Краснояров, М. А. Аргузова, Ж. А. Хужамурадов, С. Р. Рахимов // Социальные и гуманитарные науки. Отечественная и зарубежная литература. Серия 6: Языкознание. Реферативный журнал. — 2022. — № 2. — С. 41— 49. — DOI: 10.31249/ling/2022.02.02.</mixed-citation><mixed-citation xml:lang="en">Galushkin, A. I. (2022). Neural networks. In: Great Russian Encyclopedia, 16 november. Available at: https://old.bigenc.ru/technology_and_technique/text/4114009 (accessed 06.20.2023). (In Russ.).</mixed-citation></citation-alternatives></ref><ref id="cit9"><label>9</label><citation-alternatives><mixed-citation xml:lang="ru">Юхан Т. Проблемы и методы квантитативно-системного исследования лексики / Т. Юхан. — Таллин : Валгус, 1987. — 204 с.</mixed-citation><mixed-citation xml:lang="en">Golovin, B. N. (1971). Language and statistics. Moscow: Education. 190 p. (In Russ.).</mixed-citation></citation-alternatives></ref><ref id="cit10"><label>10</label><citation-alternatives><mixed-citation xml:lang="ru">Cohen A. Numerical Analysis of Word Frequencies in Artificial and Natural Language Texts / A. Cohen, R. Mantegna, S. Havlin // Fractals. — 2011. — Vol. 5, no. 01. — Pp. 1—19. — DOI: 10.1142/S0218348X97000103.</mixed-citation><mixed-citation xml:lang="en">Kettunen, K. (2014). Can Type-Token Ratio be Used to Show Morphological Complexity of Languages? Journal of Quantitative Linguistics, 21(3): 223—245. DOI: 10.1080/09296174.2014.911506.</mixed-citation></citation-alternatives></ref><ref id="cit11"><label>11</label><citation-alternatives><mixed-citation xml:lang="ru">Dale R. GPT-3: What’s it good for? / R. Dale // Natural Language Engineering. — 2021. — Vol. 27, no. 1. — Pp. 113—118. — DOI: 10.1017/S1351324920000601.</mixed-citation><mixed-citation xml:lang="en">Klee, T., Gavin, W. J., Stokes, S. F. (2017). Utterance length and lexical diversity in American and British–English speaking children: What is the evidence for a clinical marker of SLI? In: Language Disorders From a Developmental Perspective. New York. 103—140. DOI: 10.4324/9781315092041-4.</mixed-citation></citation-alternatives></ref><ref id="cit12"><label>12</label><citation-alternatives><mixed-citation xml:lang="ru">Dinesh K. Study and Analysis of Chat GPT and its Impact on Different Fields of Study / K. Dinesh, S. Nathan // International Journal of Innovative Science and Research Technology (IJISRT). — 2023. — Vol. 8, no. 3. — Pp. 827—833. — DOI: 10.5281/zenodo.7767675.</mixed-citation><mixed-citation xml:lang="en">Krasnoyarov, A. Yu., Arguzova, M. A., Khuzhamuradov, Zh. A., Rakhimov, S. R. (2022). “Speech creativity” of artificial intelligence: what texts a machine writes and how they differ from human ones. Social and Humanitarian Sciences. Domestic and foreign literature. Episode 6: Linguistics. Abstract journal, 2: 41—49. DOI: 10.31249/ling/2022.02.02. (In Russ.).</mixed-citation></citation-alternatives></ref><ref id="cit13"><label>13</label><citation-alternatives><mixed-citation xml:lang="ru">Floridi L. GPT-3: Its Nature, Scope, Limits, and Consequences / L. Floridi, M. Chiriatt // Minds and Machines. — 2020. — Vol. 30, no. 2. — Pp. 1—14. — DOI: 10.1007/s11023-020-09548-1.</mixed-citation><mixed-citation xml:lang="en">McCarthy, P. M., Jarvis, S. (2007). Voc-D: a theoretical and empirical evaluation. Language Testing, 24 (4): 459—488. DOI: 10.1177/0265532207080767.</mixed-citation></citation-alternatives></ref><ref id="cit14"><label>14</label><citation-alternatives><mixed-citation xml:lang="ru">Kettunen K. Can Type-Token Ratio be Used to Show Morphological Complexity of Languages? / K. Kettunen // Journal of Quantitative Linguistics. — 2014. — Vol. 21, no. 3. — Pp. 223—245. — DOI: 10.1080/09296174.2014.911506.</mixed-citation><mixed-citation xml:lang="en">McCarthy, P. M., Jarvis, S. (2010). MTLD, vocd-D, and HD-D: a validation study of sophisticated approaches to lexical diversity assessment. Behavior Research Methods, 42 (2): 381—392.</mixed-citation></citation-alternatives></ref><ref id="cit15"><label>15</label><citation-alternatives><mixed-citation xml:lang="ru">Klee T. Utterance length and lexical diversity in American and British–English speaking children: What is the evidence for a clinical marker of SLI? / T. Klee, W. J. Gavin, S. F. Stokes // Language Disorders From a Developmental Perspective. — New York, 2017. — Pp. 103—140. — DOI: 10.4324/9781315092041-4.</mixed-citation><mixed-citation xml:lang="en">Nasyrova, G. N., Amonova, Sh. Kh., Burnashev, R. F. (2022). Review of modern services and software of quantitative linguistics. Science and Education, 3 (12): 450—462. (In Russ.).</mixed-citation></citation-alternatives></ref><ref id="cit16"><label>16</label><citation-alternatives><mixed-citation xml:lang="ru">McCarthy P. M. Voc-D: a theoretical and empirical evaluation / P. M. McCarthy, S. Jarvis // Language Testing. — 2007. — Vol. 24, no. 4. — Pp. 459—488. — DOI: 10.1177/0265532207080767.</mixed-citation><mixed-citation xml:lang="en">Qaiser, S., Ali, R. (2018). Text Mining: Use of TF-IDF to Examine the Relevance of Words to Documents. International Journal of Computer Applications, 181 (1): 25—29.</mixed-citation></citation-alternatives></ref><ref id="cit17"><label>17</label><citation-alternatives><mixed-citation xml:lang="ru">McCarthy P. M. MTLD, vocd-D, and HD-D: a validation study of sophisticated approaches to lexical diversity assessment / P. M. McCarthy, S. Jarvis // Behavior Research Methods. — 2010. — Vol. 42, no. 2. — Pp. 381—392.</mixed-citation><mixed-citation xml:lang="en">Somers, H. H. (1966). Statistical methods in literary analysis. In: The Computer and Literary Style. Kent, OH: Kent State University. 128—140.</mixed-citation></citation-alternatives></ref><ref id="cit18"><label>18</label><citation-alternatives><mixed-citation xml:lang="ru">Qaiser S. Text Mining: Use of TF-IDF to Examine the Relevance of Words to Documents / S. Qaiser, R. Ali // International Journal of Computer Applications. — 2018. — 181 (1). — Pp. 25—29.</mixed-citation><mixed-citation xml:lang="en">Tweedie, F. J., Baayen, R. H. (1998.).How variable may a constant be? Measures of lexical richness in perspective. Computers and the Humanities, 32: 323—352.</mixed-citation></citation-alternatives></ref><ref id="cit19"><label>19</label><citation-alternatives><mixed-citation xml:lang="ru">Somers H. H. Statistical methods in literary analysis / H. H. Somers // The Computer and Literary Style / J. Leeds (еd.). — Kent, OH : Kent State University. — 1966. — Рр. 128—140.</mixed-citation><mixed-citation xml:lang="en">Yukhan, T. (1987). Problems and methods of quantitative-systematic research of vocabulary. Tallinn: Valgus. 204 p. (In Russ.).</mixed-citation></citation-alternatives></ref><ref id="cit20"><label>20</label><citation-alternatives><mixed-citation xml:lang="ru">Tweedie F. J. How variable may a constant be? Measures of lexical richness in perspective / F. J. Tweedie, R. H. Baayen // Computers and the Humanities. — 1998. — Vol. 32. — Pp. 323—352.</mixed-citation><mixed-citation xml:lang="en">Zakharova, E. Yu., Savina, O. Yu. (2020). Lexical diversity of text and ways of measuring it. Bulletin of Tyumen State University. Humanities studies. Humanities, 6 (1): 20—34. DOI: 10.21684/2411-197X-2020-6-1-20-34. (In Russ.).</mixed-citation></citation-alternatives></ref><ref id="cit21"><label>21</label><citation-alternatives><mixed-citation xml:lang="ru">Zenker F. Investigating minimum text lengths for lexical diversity indices / F. Zenker, K. Kyle // Assessing Writing. — 2021. — Vol. 47, no. 2. — DOI: 10.1016/j.asw.2020.100505.</mixed-citation><mixed-citation xml:lang="en">Zenker, F., Kyle, K. (2021). Investigating minimum text lengths for lexical diversity indices. Assessing Writing, 47 (2). DOI: 10.1016/j.asw.2020.100505.</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>
