´ëÇѾð¾îÇÐȸ ÀüÀÚÀú³Î

´ëÇѾð¾îÇÐȸ

32±Ç 3È£ (2024³â 9¿ù)

Çѱ¹¾î ¹«ÁÖ¾î ±¸¹®ÀÇ ¿µ¾î ¹ø¿ª ¾ç»ó: Àΰ£¹ø¿ª, ±¸±Û¹ø¿ª, êGPT °£ÀÇ Â÷À̸¦ Áß½ÉÀ¸·Î

ÀÓÁø

Pages : 1-22

DOI : https://doi.org/10.24303/lakdoi.2024.32.3.1

PDFº¸±â

¸®½ºÆ®

Abstract

Yim, Jin. (2024). Strategies for translating zero-subject Korean sentences into English: A focus on the differences between Human, NMT, and LLM Translations. The Linguistic Association of Korea Journal, 32(3), 1-22. This paper investigates the translation strategies employed in human and machine translations of Korean zero-subject sentences into English. The author translated 343 zero-subject segments from management forewords in business reports using Google Translate (NMT) and GPT-3.5 (LLM) and compared the results with quality human translation, seeking to investigate the patterns of three corporas translation strategiessubject restoration or structural modification. It was found that all three corpora-human translation (HT), NMT, and LLM translation-the dropped subject was most commonly replaced by personal pronouns rather than other nouns. Two statistically significant differences emerged among the corpora. First, HT exhibited a higher frequency of proper or general noun subjects, likely reflecting translators' efforts to avoid repetitive use of the first-person plural pronoun "we" in adjacent sentences. In contrast, NMT and LLM translations frequently adopted "we," leveraging it as a safe choice to enhance reader engagement in this genre. Second, NMT showed an overuse of short passive constructions without an agent, a choice underrepresented in LLM translations. While short passives can be effective when the subject is omitted in the source text, they may weaken the connection between action and agent, thereby altering the original discourse effect. This study contributes to the MT literature by expanding the scope to include genre- specific features, LLM translation tendencies, and particular translation challenges.

Keywords

# ±â°è¹ø¿ª(machine translation) # ½Å°æ¸Á±â°è¹ø¿ª(neural machine translation) # ´ë±Ô¸ð¾ð¾î¸ðµ¨(large language model) # ¹«ÁÖ¾î(zero subject) # ÇÑ¿µ¹ø¿ª(Korean-English translation)

References

  • °­µ¿Èñ. (2023). ³ëÇÑ ¹®ÇÐ ¹ø¿ª¿¡¼­ ³ªÅ¸³­ »ý·«°ú ȯ¿øÀÇ ¾ç»ó °íÂû: ¹®Ã¼¿Í ¹ø¿ª Àü·« ÀÇ °üÁ¡¿¡¼­. ¹ø¿ªÇבּ¸, 24(1), 253-278.
  • °í¿µ±Ù, ±¸º»°ü. (2018). ¿ì¸®¸» ¹®¹ý·Ð. Áý¹®´ç.
  • ±¹¸³±¹¾î¿ø. (n.d.) Ç¥Áر¹¾î´ë»çÀü. Retrieved July 19, 2024, from https://stdict.korean. go.kr/main/main.do
  • ±è°æÈñ. (2020). ÁÖ°Ý ÀÎĪ´ë¸í»çÀÇ »ý·«°ú ¹ø¿ª. Åë¹ø¿ª±³À°¿¬±¸, 18(4), 97-118.
  • ±è¼öÁ¤. (2016). ¹®¾î ÅؽºÆ®ÀÇ À帣º° ÁÖ¾îÀÇ ½ÇÇö ¾ç»ó. ÇѹÎÁ·¾î¹®ÇÐ, 72, 25-62.
  • ±èÀÚ°æ. (2021). Æ÷½ºÆ®¿¡µðÆà °á°ú¹°ÀÇ Á¤È®¼º ¿À·ù °íÂû. Å뿪°ú ¹ø¿ª, 23(3), 29-58.
  • ±èÇѽÄ, °­µ¿Èñ, ³²½½±â, ¼­½ÂÈñ, ¼®ÁÖÈñ, ¼Û½Å¾Ö, ÃÖÁö¼ö, & È«½Âºó. (2019). ÀÎĪ´ë¸í»ç »ý·« ¹®ÀåÀÇ A-B ¹ø¿ª ¾ç»ó. Å뿪°ú ¹ø¿ª, 21(3), 31-54.
  • ±èÇö¾Æ. (2012). ¹ø¿ª ¹× ºñ¹ø¿ª<ÁÖÁÖ¿¡°Ô º¸³»´Â ÆíÁö>¿¡ ±¸ÃàµÈ ÀúÀÚ¿Í µ¶ÀÚÀÇ »óÈ£ÀÛ ¿ë: ÅؽºÆ®Àû ¸ÞŸ´ãÈ­ ºÐ¼®À» Áß½ÉÀ¸·Î. Åë¹ø¿ªÇבּ¸, 16(2), 115-137.
  • ¹®±Í¼±. (2010). ¿µ³íÇ×ÀÇ ¼Ó¼º ÀçÁ¶¸í. ¾ð¾îÇÐ, 18(1), 67-92.
  • ¹Ú¼öÁ¤, ÃÖÀº½Ç. (2023). êGPTÀÇ ¾ÆÀÌ·¯´Ï ¹ø¿ª È°¿ë °¡´É¼º °íÂû. ¹ø¿ªÇבּ¸, 24(2), 131-160.
  • ¹Ú¿Á¼ö. (2018). ¿øõ¾ð¾îÀÇ °üÁ¡¿¡¼­ »ìÆ캻 ±â°è¹ø¿ªÀÇ ¿À·ùºÐ¼®°ú ¼öÁ¤ ¿øÄ¢: ºñ¹®ÇÐ ÅؽºÆ®ÀÇ Åë»çÀû Ư¡¿¡ ±Ù°ÅÇؼ­. µ¿¾ÆÀι®ÇÐ, 44, 151-171
  • ¹ÚûÈñ. (2012). Çѱ¹¾î¿Í ¿µ¾îÀÇ »ý·« Çö»ó¿¡ ´ëÇÑ Åë°èÀû Á¢±Ù. ¾î¹®³íÁý, 66, 171-191.
  • º¯±æÀÚ. (2024). ¿µ¾î¼öµ¿¹®ÀÇ Çѱ¹¾î ¹ø¿ª¿¡ ´ëÇÑ ºñ±³ ºÐ¼®: ±â°è¹ø¿ª°ú Çкλý ¹× Åë¹ø¿ªÀü°ø´ëÇпø»ýÀÇ Æ÷½ºÆ®¿¡µðÆà Áß½ÉÀ¸·Î. ¾ð¾îÇבּ¸, 29(1), 25-50.
  • ¼­À¯±Ù. (2024). ´ëÇÑÇ×°ø ÀϹݼ®¿¡¼­ ÄŶó¸é ¾È ÁÖ±â·Î...ÀÌÀ¯´Â? Á¶¼±ÀϺ¸. Retrieved August 5, 2024, from https://www.chosun.com/economy/industry-company/ 2024/08/01/C2B3 CZAVEVBY7EZA72GMKGVWFE/
  • ½Åõ, Á¶ÇýÁø. (2024). À§È­ ¼Ò¼³ Çã»ï°ü ¸ÅÇ÷±â ÁßÇѹø¿ªÀ» ÅëÇØ º» ¹®Çйø¿ª¿¡¼­ÀÇ ÃªGPTÀÇ È°¿ë °¡´É¼º. ¾ð¾îÇבּ¸, 29(1), 51-65.
  • ¿Õûµ¿. (2024). ´ë¸¸ÀÎ Çѱ¹¾î ÇнÀÀÚÀÇ ÇÑÁß ¹®Àå ´ë¿ª ¾ç»ó-´ëÈ­¹® Á־ Áß½ÉÀ¸·Î. ¾Æ½Ã¾Æ¹®È­ÇÐÁö, 3, 115-141.
  • ÀÌÀ¯Á¤. (2023). Çö´ë½Ã ÀΰøÁö´É(AI) ¹ø¿ªÀÇ ¿À·ù ¾ç»ó ¿¬±¸. ¹®È­¿ÍÀ¶ÇÕ, 45(10), 97-110.
  • ÀÌÁöÀº, ÃÖÈ¿Àº. (2020). ÄÚÆÛ½º ¿¬±¸¸¦ ÅëÇØ »ìÆ캻 ¹ý·É ¹ø¿ª ÅؽºÆ®ÀÇ ¾ð¾îÀû Ư¼º: ¼öµ¿Å ±¸¹®À» Áß½ÉÀ¸·Î. ¹ø¿ªÇבּ¸, 21(2), 251-284.
  • ÀÌÁöÀº, ÃÖÈ¿Àº. (2023). ¿øõÅؽºÆ® ³­À̵µ¿Í ±â°è¹ø¿ª Ç°Áú¿¡ ´ëÇÑ °íÂû-±¸±Û ÇÑ¿µ ¹ý ·É¹ø¿ª »ç·Ê¸¦ Áß½ÉÀ¸·Î. ¾ð¾îÇבּ¸, 28(1), 77-101.
  • ÀÌâ¼ö. (2014). ¹ø¿ªÇѱ¹¾î¿Í ºñ¹ø¿ªÇѱ¹¾î °£ Ÿµ¿Çü °¨Á¤±¸¹®¿¡¼­ÀÇ ¹«»ý¹° ÁÖ¾î »ç ¿ë Â÷ÀÌ ¿¬±¸. Åë¹ø¿ªÇבּ¸, 18(1), 123-141.
  • ÀÓ¼ÒÁ¤, À̾ÆÇü. (2024). ÇÑÁß ¹ø¿ª¿¡¼­ÀÇ ÀÎĪ´ë¸í»ç ÁÖ¾î ó¸® ¾ç»ó ´ëÁ¶¡ª¼Ò¼³ ¡¶ÇÁ¶ó ÀÚÈ£ÅÚ¡·À» Áß½ÉÀ¸·Î. Áß±¹¹®ÇÐ, 118, 137-159.
  • Àü¼³ÁÖ. (2024). Çѱ¹¾î ¸ð¾î È­ÀÚ¿Í Áß±¹ÀÎ Çѱ¹¾î ÇнÀÀÚÀÇ ¿µÁÖ¾î ÀÇ¹Ì Çؼ® ¾ç»ó. »ç ȸ¾ð¾îÇÐ, 32(2), 79-107.
  • Á¤¿¬Ã¢. (2007). ÁÖ¾î »ý·«¿¡ ´ëÇÑ ¼Ò°í. ¾ð¾î°úÇÐ, 14(2), 101-120.
  • Á¶½Â¿¬. (2023). Àΰ£¹ø¿ª°ú ±â°è¹ø¿ªÀÇ ¿©¼º¾î¡¤ ³²¼º¾î ºñ±³ ¿¬±¸: ÇÑÀÏ ¹ø¿ªº» [82³â»ý ±èÁö¿µ] ÀÇ ¹®¸» (ÙþØÇ) Ç¥ÇöÀ» Áß½ÉÀ¸·Î. ¾ð¾îÇÐ, 31(1), 45-63.
  • Áø½Ç·Î, °ûÀºÁÖ. (2013). ¹ø¿ª¼ö¾÷ 101. Çѱ¹¹®È­»ç.
  • ÃÖÈ¿Àº. (2024). ´ëÁß°úÇÐÀÇ ¿µÇÑ ¹ø¿ª¿¡ À־ Àΰ£ ¹ø¿ª°ú ChatGPT ¹ø¿ªÀÇ ¸í½ÃÈ­ (explicitation) ¾ç»ó °íÂû - ÀÇ Ç¥Á¦ ºÐ¼®À» Áß½ÉÀ¸·Î -. T&I Review, 14(1), 149-175.
  • Çѱ¹°Å·¡¼Ò. (n.d.). KTOP30. Retrieved August 8, 2024, from http://data.krx.co.kr/con tents/MDC/EASY/visualController/MDCEASY500.cmd
  • ÇÑÇöÈñ. (2020). ÇÑ-³ë ±â°è ¹ø¿ª, ¾îµð±îÁö ¿Ô³ª?: Google°ú Papago ¹ø¿ª ¼º´É ºñ±³¸¦ ±â¹ÝÀ¸·Î. ³ë¾î³ë¹®ÇÐ, 32(3), 63-93.
  • Asay, H. S., Libby, R., & Rennekamp, K. (2018). Firm performance, reporting goals, and language choices in narrative disclosures. Journal of Accounting and Economics, 65(2-3), 380-398.
  • Baker, M. (1992). In other words: A coursebook on translation. Routledge.
  • Bakker, M., Koster, C., & Van Leuven-Zwart, K. (2009). Shifts. In M. Baker & G. Saldanha (Eds.), Routledge encyclopedia of translation studies (2nd edition) (pp. 269-273). Routledge.
  • Biber, D., Stig Johansson, Leech, G., Conrad, S., & Finegan, E. (1999). Longman grammar of spoken and written English (6th ed). Longman
  • Catford, J. (1965). A linguistic theory of translation: An essay in applied linguistics. Oxford University Press.
  • Huang, Y., & Rose, K. (2018). You, our shareholders: Metadiscourse in CEO letters from Chinese and Western banks. Text and Talk, 38(2), 167-190.
  • Hyland, K. (2005). Metadiscourse: Exploring interaction in writing. Continuum.
  • Junge, S. (2011). Corporate rhetoric in English and Japanese business reports. In S. Kranich, V. Becher, S. Hoder, & J. House (Eds.), Multilingual discourse production: Diachronic and synchronic perspectives (pp. 209-232). John Benjamins Publishing Company.
  • Kiaer, J. (2018). Korean Translation. Routledge.
  • Klaudy, K. (2009). Explicitation. In M. Baker & G. Saldanha (Eds.), Encyclopedia of Translation Studies (pp. 104-108). Routledge.
  • Nida, E. A. (1964). Toward a science of translating: With special reference to principles and procedures involved in Bible translating. Brill.
  • SciPy 1.14.0, Eric Jones, Travis Oliphant, Pearu Peterson and others. Title: SciPy: Open Source Scientific Tools for Python.
  • Seo, Y., & Lee, J. (2024). Korean Air to stop serving cup noodles in economy class. Chosun Daily. Retrieved August 5, 2024, from https://www.chosun.com/english /national-en/2024/08/01/26MU2JWNV5G4VOH256OM7NUKIQ/
  • Van Rossum, G., & Drake, F. L. (2009). Python 3 Reference Manual. Scotts Valley, CA: CreateSpace.
  • Wang, K., Zhao, X., Li, Y., & Peng, W. (2023). Prose: A pronoun omission solution for Chinese-English spoken language translation. Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing, 2297-2311.
  • Yim, J. (2024). Sentence length and translation: A comparative review of human, NMT, and LLM translations. T&I Review, 14(1), 69-93.
  • Yim, J., & Lee, Y. (2024). Sensitivity of translation universals to genre/ register variations: Focused on corporate reporting. The Linguistic Association of Korea Journal, 32(2), 153-173.