Metaphor translation at natural language processing: A practical solution of the problem
DOI :
https://doi.org/10.33910/2686-830X-2026-8-1-31-42Mots-clés :
metaphorical lexis, secondary nomination in oil and gas domain, natural language processing, scientific-technical text, computational lexicographyRésumé
The article is dedicated to the appropriate delivery of metaphoric expression as the one of the most complex issues in the realm of automated translation. Thematic justification is based on the rapid advancement of neural technology in natural language processing which, despite the significant progress, continue to demonstrate systematic deviances in the secondary nomination units’ interpretation and translation. The research material of the article uses terminological units extracted from contemporary English-language scientific and technical text of oil and gas domain; these units are formed in a semantic way, namely via metaphorical transfer. Metaphor, being the connection link between mental and language structures, remains up to now a challenging task for computer algorithms. The author, within the article scope, does not aim to analyze fundamental reasons of current automated translation systems’ failures in metaphoric vocabulary processing. It is the secondary nomination units’ complexity that is in the article’s focus, wherein the direct denotative meaning of the word is replaced by the figurative and idiomatic meaning, rooted in a specific cultural and discourse context. Inability of modern computer technologies to recognize this contextual shift and interpret it properly leads to literal translation and loss of expressiveness. The article aim is to demonstrate the tools of computer lexicology as a possible way of solving the problem of inaccurate metaphor transfer in special-purpose texts. It is proposed to integrate special dynamic glossary of metaphoric models into the automated translation architecture as an external module of semantic support. The glossary is targeted to metaphoric structures identification in a source text and translation results’ generation. The glossary integration into existing neural network architecture does not change it, but significantly supplements allowing smoothing over the “cognitive gap” in figurative speech processing. Practical relevance of using modern lexicographic instrumentarium of applied linguistics involves the significant improvement of adequacy and naturalness of automated translation of texts’ domain, where metaphor is an integral stylistic device.
Références
ИСТОЧНИКИ
Hahn, R., Schumacker, E., Bowman, M. (2020) Shell drills u-turn lateral well in Permian basin. Oil and Gas Journal. International Petroleum News and Technology. [Online]. Available at: https://digital.ogj.com/ogjournal/library/page/20200504/29/ (accessed 05.09.2025).
Oil and Gas Journal. International Petroleum News and Technology (January 2019 — January 2021). PennWell Corporation, Tulsa (USA). [Online]. Available at: https://digital.ogj.com/OilandGasJournal/20201214/MobilePagedReplica.action?utm_source=newsletter&utm_medium=email&utm_campaign=TXOGJO201211003&utm_content=gtxcel&pm=2&folio=Cover#pg1 (accessed 05.09.2025).
СЛОВАРИ
Булатов, А. И., Пальчиков, В. В. (2001) Англо-русский словарь по нефти и газу. М.: РУССО, 400 с.
Кедринский, В. В. (2004) Англо-русский словарь по химии и переработке нефти. М.: РУССО, 768 с.
Морозов, Н. В. (2010) Англо-русский и русско-английский словарь по нефти и газу. Компактное издание. M.: Живой язык, 512 с.
Recommended Practice for Drill Stem Design and Operating Limits. (2003) American Petroleum Institute. [Online]. Available at: https://www.api.org/~/media/files/publications/addenda-and-errata/exploration-production/7g_add-2.pdf?la=en (accessed 19.02.2026).
Dog leg. (2025) Collins Dictionary and Thesaurus. [Online]. Available at: https://www.collinsdictionary.com/search/?dictCode=english&q=dog-leg (accessed 05.09.2025).
Dog-leg. (2025a) Merriam-Webster Dictionary. [Online]. Available at: https://www.merriam-webster.com/dictionary/dogleg (дата обращения 05.09.2025).
Dog-leg. (2025b) Online Etymology dictionary. [Online]. Available at: https://www.etymonline.com/search?q=dog-leg (accessed 05.09.2025).
Horseshoe. (2025a) Merriam-Webster Dictionary. [Online]. Available at: https://www.merriam-webster.com/dictionary/horseshoe (accessed 05.09.2025).
Horseshoe. (2025b) Online Etymology dictionary. [Online]. Available at: https://www.etymonline.com/search?q=horseshoe (accessed 05.09.2025).
ЛИТЕРАТУРА
Беляева, Л. Н. (2019) Машинный перевод в работе переводчика: практический аспект. Вестник Пермского национального исследовательского политехнического университета. Проблемы языкознания и педагогики, № 2, с. 8–20. https://doi.org/10.15593/2224-9389/2019.2.1
Беляева, Л. Н. (2022) Машинный перевод в современной технологии процесса перевода. Известия РГПУ им. А. И. Герцена, № 203, с. 22–30. https://doi.org/10.33910/1992-6464-2022-203-22-30
Калинина, С. В. (2024) Структурно-семантические и функциональные особенности англоязычной терминологии нефтегазовой сферы. Диссертация на соискание степени кандидата филологических наук. СПб.: РГПУ им. А. И. Герцена, 271 с.
Камшилова, О. Н., Беляева, Л. Н., Пиотровская, К. Р. (2023) Инженерная и прикладная лингвистика сегодня: хроника IV Международной конференции «Пиотровские чтения — 2022». Terra Linguistica, т. 14, № 1, с. 98–107. https://doi.org/10.18721/JHSS.14109
Кобрина, Н. А. (2013) О соотносимости ментальной сферы и вербализации: взаимозаменяемость / относительная автономность / неоднозначность векторной зависимости. В кн.: Трунова О. В (ред.). Язык: мультидисциплинарность научного знания: научный альманах. Вып. 3. Барнаул: Изд-во Алтайской государственной педагогической академии, с. 10–22.
Лакофф, Дж., Джонсон, М. (2004) Метафоры, которыми мы живем. М.: Едиториал УРСС, 256 с.
Лейчик, В. М. (2022) Терминоведение: Предмет, методы, структура. 6-е изд. М.: ЛЕНАНД, 248 с.
Ли, И. (2025) Перевод русских метафорических наименований посредством большой языковой модели. Современное педагогическое образование, № 12, с. 211–215.
Липченко, А. Д. (2025) Оценка качества машинного перевода метафорических медицинских терминов. В кн.: Ю. И. Бушенева (ред.) Актуальные проблемы науки: взгляд студентов: Материалы IV Всероссийской студенческой научной конференции. СПб.: Изд-во Ленинградского государственного университета им. А. С. Пушкина, с. 138–142.
Лукьянова, В. С. (2022) Особенности обучения переводу метафоры в экономическом тексте. В кн.: Русинова Н. В. (ред.) Переводчик 2030: обучение профессионально ориентированному переводу в меняющемся мире. Сборник научных статей международной научно-практической конференции, приуроченной к празднованию Дня преподавателя перевода. Одинцово: Изд-во Московского государственного института международных отношений, с. 68–73.
Серебренников, Б. А., Уфимцева А. А. (ред.). (1977). Языковая номинация (Общие вопросы). М.: Наука, 359 с.
Суперанская, А. В., Подольская, Н. В., Васильева, Н. В. (2012) Общая терминология: Вопросы теории. 6-е изд. М.: Либроком, 248 с.
Тихонова, И. Б. (2022) Green technology: метафора цвета в профессиональном дискурсе. Вестник Кемеровского государственного университета, т. 24, № 1, с. 129–137. https://doi.org/10.21603/2078-8975-2022-24-1-129-137
Хабарова, Е. М. (2023) Машинный перевод выразительных средств — метафор. Философские проблемы информационных технологий и киберпространства, № 2 (24), с. 108–119. https://doi.org/10.17726/philit.2023.2.8
He, Z., Liang, T., Jiao, W. et al. (2024) Exploring human-like translation strategy with large language models. Transactions of the Association for Computational Linguistics, vol. 12, pp. 229–246. https://doi.org/10.1162/tacl_a_00642
Hovy, D., Srivastava, S., Jauhar, S. K. et.al. (2013) Identifying metaphorical word use with tree kernels. In: Proceedings of the first workshop on metaphor in NLP. Atlanta: Association for Computational Linguistics Publ., pp. 52–57.
Knowles, R., Larkin, S., Tessier, M., Simard, M. (2023) Terminology in neural machine translation: A case study of the Canadian Hansard. In: Proceedings of the 24th annual conference of the European Association for machine translation. Tampere: European Association for Machine Translation Publ., pp. 481–488.
Popel, M., Tomkova, M., Tomek, J. et al. (2020) Transforming machine translation: A deep learning system reaches news translation quality comparable to human professionals. Nature Communications, vol. 11, article 4381. https://doi.org/10.1038/s41467-020-18073-9
Shutova, E. (2010) Models of metaphor in NLP. In: Proceedings of the 48th annual meeting of the association for computational linguistics. Stroudsburg: Association for Computational Linguistics Publ., pp. 688–697.
Wang, H., Wu, H., He, L. et al. (2022) Progress in machine translation. Engineering, vol. 18, pp. 143–153. https://doi.org/10.1016/j.eng.2021.03.023
SOURCES
Hahn, R., Schumacker, E., Bowman, M. (2020) Shell drills u-turn lateral well in Permian basin. Oil and Gas Journal. International Petroleum News and Technology. [Online]. Available at: https://digital.ogj.com/ogjournal/library/page/20200504/29/ (accessed 05.09.2025). (In English)
Oil and Gas Journal. International Petroleum News and Technology (January 2019 — January 2021). PennWell Corporation, Tulsa (USA). [Online]. Available at: https://digital.ogj.com/OilandGasJournal/20201214/MobilePagedReplica.action?utm_source=newsletter&utm_medium=email&utm_campaign=TXOGJO201211003&utm_content=gtxcel&pm=2&folio=Cover#pg1 (accessed 05.09.2025) (In English)
DICTIONARIES
Bulatov, A. I., Pal’chikov, V. V. (2001) English-Russian dictionary on oil and gas. Moscow: RUSSO Publ., 400 p. (In Russian)
Recommended Practice for Drill Stem Design and Operating Limits. (2003) American Petroleum Institute. [Online]. Available at: https://www.api.org/~/media/files/publications/addenda-and-errata/exploration-production/7g_add-2.pdf?la=en (accessed 19.02.2026). (In English).
Dog leg. (2025) Collins Dictionary and Thesaurus. [Online]. Available at: https://www.collinsdictionary.com/search/?dictCode=english&q=dog-leg (accessed 05.09.2025). (In English).
Dog-leg. (2025a) Merriam-Webster Dictionary. [Online]. Available at: https://www.merriam-webster.com/dictionary/dogleg (accessed 05.09.2025). (In English).
Dog-leg. (2025b) Online Etymology dictionary. [Online]. Available at: https://www.etymonline.com/search?q=dog-leg (accessed 05.09.2025). (In English)
Horseshoe. (2025a) Merriam-Webster Dictionary. [Online]. Available at: https://www.merriam-webster.com/dictionary/horseshoe (accessed 05.09.2025). (In English).
Horseshoe. (2025b) Online Etymology dictionary. [Online]. Available at: https://www.etymonline.com/search?q=horseshoe (accessed 05.09.2025). (In English).
Kedrinskyij, V. V. (2004) English-Russian dictionary of petroleum chemistry and refining. Moscow: RUSSO Publ., 768 p. (In Russian)
Morozov, N. V. (2010) Compact English-Russian and Russian-English dictionary of oil and gas. Moscow: Zhivoj yazyk Publ., 512 p. (In Russian)
REFERENCES
Belyaeva, L. N. (2019) Machine translation in a translator workflow: Practical view. PNRPU Linguistics and Pedagogy Bulletin, no. 2, pp. 8–20. https://doi.org/10.15593/2224-9389/2019.2.1 (In Russian)
Belyaeva, L. N. (2022) Machine translation and modern translation technology. Izvestia: Herzen University Journal of Humanities & Sciences, no. 203, pp. 22–30. https://doi.org/10.33910/1992-6464-2022-203-22-30 (In Russian)
He, Z., Liang, T., Jiao, W. et al. (2024) Exploring human-like translation strategy with large language models. Transactions of the Association for Computational Linguistics, vol. 12, pp. 229–246. https://doi.org/10.1162/tacl_a_00642 (In English)
Hovy, D., Srivastava, S., Jauhar, S. K. et.al. (2013) Identifying metaphorical word use with tree kernels. In: Proceedings of the first workshop on metaphor in NLP. Atlanta: Association for Computational Linguistics Publ., pp. 52–57. (In English)
Kalinina, S. V. (2024) Structural, semantic, and functional features of the English-language terminology in the oil and gas industry. PhD dissertation (Philology). Saint Petersburg: Herzen State Pedagogical University of Russia, 271 p. (In Russian)
Kamshilova, О. N., Belyaeva, L. N., Poitrovskaja, К. R. (2023) Language engineering and applied linguistics today: The chronicle of the IV International conference “R. Piotrowski’s Readings – 2022”. Terra Linguistica, no. 14, iss. 1, pp. 98–107. https://doi.org/10.18721/JHSS.14109 (In Russian)
Khabarova, E. M. (2023) Machine translation of expressive means — metaphors. Philosophical problems of IT and Cyberspace, no. 2 (24), pp. 108–119. https://doi.org/10.17726/philit.2023.2.8 (In Russian)
Knowles, R., Larkin, S., Tessier, M., Simard, M. (2023) Terminology in neural machine translation: A case study of the Canadian Hansard. In: Proceedings of the 24th Annual Conference of the European Association for Machine Translation. Tampere: European Association for Machine Translation Publ., pp. 481–488. (In English)
Kobrina, N. A. (2013) On Correlation of Mental Sphere and Verbalization: Interchangeability / Relative Autonomy / Ambiguity of Vector Dependency. In: Trunovoj O. V (ed.). Language: Multidisciplinary scholarly knowledge. Iss. 3. Barnaul: Altai State Pedagogical Academy Publ., pp. 10–22. (In Russian)
Lakoff, G., Johnson, M. (2004) Metaphors we live by. Moscow: Editorial URSS Publ., 256 p. (In Russian)
Lejchik, V. M. (2022) Terminology science: Theme, methods, structure. 6th ed. Moscow: LENAND Publ., 248 p. (In Russian)
Li, I. (2025) Translation of Russian metaphorical names using a large-scale language model. Modern Pedagogical Education, no. 12, pp. 211–215. (In Russian)
Lipchenko, A. D. (2025) Evaluation of machine translation of metaphorical medical terms. In: Yu. I. Busheneva (ed.) Actual problems of science: students’ view: Abstracts of IV All Russian student scholarly congress. Saint Petersburg: Pushkin Leningrad State University Publ., pp. 138–142. (In Russian)
Luk’yanova, V. S. (2022) Teaching Within an Economic Text. In: Rusinova N. V. (ed.). Translator 2030: Teaching professionally oriented translation in a changing world. Collection of Scientific articles from the international scientific and practical conference dedicated to the celebration of translation Teacher’s Day. Odintsovo: MGIMO University Publ., pp. 68–73. (In Russian)
Popel, M., Tomkova, M., Tomek, J. et al. (2020) Transforming machine translation: A deep learning system reaches news translation quality comparable to human professionals. Nature Communications, vol. 11, article 4381. https://doi.org/10.1038/s41467-020-18073-9 (In English)
Serebrennikov, B. A., Ufimceva A. A. (eds.). (1977). Language nomination (General questions). Moscow: Nauka Publ., 359 p. (In Russian)
Superanskaya, A. V., Podol’skaya, N. V., Vasil’eva, N. V. (2012) General Terminology: Theoretical Issues. 6th ed. Moscow: Librokom Publ., 248 p. (In Russian)
Shutova, E. (2010) Models of metaphor in NLP. In: Proceedings of the 48th annual meeting of the association for computational linguistics. Stroudsburg: Association for Computational Linguistics Publ., pp. 688–697. (In English)
Tikhonova, I. B. (2022) Green technology: Color metaphor in professional discourse. The Bulletin of Kemerovo State University, vol. 24, no. 1, pp. 129–137. https://doi.org/10.21603/2078-8975-2022-24-1-129-137 (In Russian)
Wang, H., Wu, H., He, L. et al. (2022) Progress in Machine Translation. Engineering, vol. 18, pp. 143–153. https://doi.org/10.1016/j.eng.2021.03.023 (In English)
Téléchargements
Publiée
Numéro
Rubrique
Licence
(c) Copyright Svetlana V. Kalinina 2026
Ce travail est disponible sous la licence Creative Commons Attribution 4.0 International .
The work is provided under the terms of the Public Offer and of Creative Commons public license Creative Commons Attribution 4.0 International (CC BY 4.0).
This license permits an unlimited number of users to copy and redistribute the material in any medium or format, and to remix, transform, and build upon the material for any purpose, including commercial use.
This license retains copyright for the authors but allows others to freely distribute, use, and adapt the work, on the mandatory condition that appropriate credit is given. Users must provide a correct link to the original publication in our journal, cite the authors' names, and indicate if any changes were made.
Copyright remains with the authors. The CC BY 4.0 license does not transfer rights to third parties but rather grants users prior permission for use, provided the attribution condition is met. Any use of the work will be governed by the terms of this license.
