Earticle

현재 위치 Home

Issues

통역과 번역 [Interpretation and Translation]

간행물 정보
  • 자료유형
    학술지
  • 발행기관
    한국통역번역학회 [Korean Society of Interpretation and Translation Studies]
  • pISSN
    1229-6074
  • eISSN
    3140-1937
  • 간기
    연3회
  • 수록기간
    1999 ~ 2026
  • 등재여부
    KCI 등재
  • 주제분류
    인문학 > 통역번역학
  • 십진분류
    KDC 717 DDC 400
많이 이용된 논문 (최근 1년 기준)
No
1

이용수:234회 인공지능(AI)기술의 전문통역 교육 활용 방안 : 챗GPT를 중심으로

김혜림

한국통역번역학회 통역과 번역 제26권 2호 2024.08 pp.27-65

※ 기관로그인 시 무료 이용이 가능합니다.

8,400원

With the recent significant advancements in AI technology, the internal and external environment of interpretation education is rapidly changing. In particular, the generative AI tool ChatGPT-4 has shown a remarkable improvement compared to previous versions. Given these developments, this study aims to explore ways to integrate AI technology into professional interpretation education. To this end, the study will first analyze the performance of AI interpreters at present and compile recent AI-based interpretation research published in academia. Using these observations, the study will explore the feasibility of applying AI tools to professional interpretation practice. Second, the study seeks to provide opportunities for interpretation professionals to leverage these technological advancements to enhance their capabilities by proposing methods to integrate AI technology into future interpretation education programs. In doing so, the study aims to offer an understanding of how AI technology can complement and expand human linguistic and non-linguistic abilities and provide important insights into the future development direction of the interpretation field.

2

이용수:54회 생성형 AI 프롬프팅과 번역 효과에 관한 연구

곽은주, 탁진영, 전현주

한국통역번역학회 통역과 번역 제27권 1호 2025.04 pp.1-39

※ 기관로그인 시 무료 이용이 가능합니다.

8,400원

Generative AI has revolutionized machine translation (MT) by enabling customizable outputs through prompt engineering. Unlike traditional neural machine translation (NMT) systems such as Google Translate and DeepL, which rely on predefined translation patterns, models like GPT-4 allow users to refine translation quality through different prompting strategies. This study examines the impact of Zero-shot, Few-shot, Style-specific, and Step-by-step prompting on translation quality and evaluates the effectiveness of Auto Prompt Optimization (APO) in further enhancing performance. Using GPT-4, translations were conducted for Korean-to-English, Japanese, Chinese (Ko→En, Ja, Zh) language pairs. The study assessed BLEU, TER, and COMET scores to measure accuracy, fluency, and semantic consistency. Results show that Few-shot and Step-by-step prompting significantly improve translation quality, while APO further enhances BLEU scores and reduces TER values across all prompting types. Findings also indicate that prompt effectiveness varies by language pair, emphasizing the need for language-specific prompt strategies. This study provides empirical evidence of how prompt engineering influences AI translation quality and offers strategic guidelines for optimizing translation performance.

3

이용수:51회 AI 번역 시대, 번역과 번역자를 바라보는 다양한 관점들

이상빈

한국통역번역학회 통역과 번역 제26권 3호 2024.12 pp.125-151

※ 기관로그인 시 무료 이용이 가능합니다.

6,600원

This essay provides a multifaceted analysis of the evolving landscape of translation and the changing role of human translators in the age of Generative AI. The first chapter introduces key issues by exploring how AI has replicated and surpassed human cognitive capabilities. The second chapter examines the rise of AI-driven automation in the context of Karl Marx’s anti-capitalist critique, highlighting its impact on the depreciation of human translation labor. The third chapter draws on Albert Camus’s existentialist view of Sisyphus to put an optimistic interpretation on the act of translation. The fourth chapter adopts a critical posthumanist framework to discuss the wider implications of the translation network increasingly dominated by AI agents (machine translators). The fifth chapter explores the potential of a “post-translation” or “post-translator” perspective, focusing on emerging phenomena such as “flattening” and “paratranslation.” The sixth chapter delves deeply into the cyborgization of human-machine translation and its ethical implications. Specifically, this chapter envisions “translation trademark symbols” (e.g., TRANSLATION™, TRANSLATION®) and discusses how Lawrence Venuti’s notion of visibility gains renewed significance in the AI era.

4

이용수:46회 제미나이와 구글은 인간번역 문체에 얼마나 가까워졌나 : 5개 언어, 5개 머신러닝 활용연구

정혜연, 김선경, 김해연, 류두진, 유은미, 최재걸, 최혜림

한국통역번역학회 통역과 번역 제27권 3호 2025.11 pp.257-284

※ 기관로그인 시 무료 이용이 가능합니다.

6,700원

This study quantitatively examines stylistic differences between human and machine translation in literary texts. A parallel corpus was constructed from five source languages-German, Arabic, Indonesian, Japanese, and Chinese-each translated into Korean by professional human translators and two machine translation systems, Google Translate and Gemini. Using five machine learning algorithms (Decision Tree, Random Forest, XG-Boost, t-SNE, and PCA), we analyzed a range of stylometric features to determine the separability of human and machine outputs. Our results show that human and machine translations are highly distinguishable, with classification models achieving over 90%accuracy. Gemini’s stylistic profile aligned more closely with that of Google Translate than with human translators. The analysis revealed comma ratio as the strongest discriminator, followed by sentence count and pronoun ratio. These findings provide empirical evidence of a persistent stylistic gap between human and machine translation in the literary domain and identify specific linguistic features that mark this divide.

5

7,200원

In undergraduate interpreter training, students are more likely to encounter bilateral interpreting between two working languages than conference interpreting, either during their studies or future careers. However, dialogue interpreting classes often present challenges due to students' limited linguistic competence and lack of subject knowledge. To address these difficulties, this study explores how students use generative AI to create dialogue scripts for interpreting practice, focusing on prompt literacy, AI-generated text features, and learners' perceptions. Students worked in small groups to generate weekly dialogue scripts on assigned topics using ChatGPT. These scripts were then enacted in class as role-plays, with each student taking a participant's role. Spontaneous interpreting was performed by other students selected by the instructor. Each group submitted full logs of their prompts and AI-generated outputs weekly and completed a survey at the end of the semester. The findings indicate that students' prompting strategies generally aligned with expert techniques and improved over time. The generated scripts proved suitable as source texts for interpreting exercises, requiring only minor revisions. Furthermore, the dialogues displayed a strong sense of realismand authenticity, enhancing learner immersion and engagement. Overall, students responded positively to the use of ChatGPT in script preparation. This study highlights the pedagogical potential of generative AI in undergraduate interpreter education.

6

이용수:45회 한 - 영 시 번역 텍스트에서 활용된 의성어 · 의태어 번역 전략

노진서

한국통역번역학회 통역과 번역 제10권 1호 2008.06 pp.45-63

※ 기관로그인 시 무료 이용이 가능합니다.

5,400원

Onomatopoeia is a difficult constituent in translation because it has different characteristics which prevent source and target text readers from communicating each other. Most of target text readers are unable to have knowledge to understand connotations of the exotic onomatopoeia elements in the source text. Accordingly the translator has to be a mediator to bridge the gap in understanding onomatopoeic expressions and help the target text readers to share the equivalent connotations of them. The purpose of this paper is to examine the translation problems in translating Korean poetry texts into English ones by focusing on onomatopoeic expressions which appear in the translation process. This paper has shown that the poetic phrases of Korean related to onomatopoeic expressions are translated into those of English by various strategies, for example, paraphrase, substitution and omission which have active and diverse compensation mechanisms.

7

7,900원

This study systematically analyzes Korean scholarship on generative AI in translation and interpreting, examining 77 research articles published between 2023 and 2025 in three major Korean journals. Drawing on Christensen et al.‘s (2017) tripartite classification, the study develops an extended coding framework to map methodological trends and identify research gaps in the field. The findings reveal sharp increase in AI-related publications, rising from 14 articles in 2023 to 37 in 2025. Translation and interpreting education (37.7%) and quality evaluation (27.3%) dominate the research agenda, followed by theoretical and critical discussions (13.0%). Empirical studies constitute the majority (77.9%), with textual analysis and survey methods being the most prevalent. Korean-to-English language pair remains the most studied (70.4% of language-specific studies), while explicit theoretical grounding appears only in 27.2% of the articles. These patterns suggest the Korean translation and interpreting research in the generative AI era is largely practice-driven and pedagogy-centered in the era of AI. The study identifies key gaps — including the underrepresentation of prompt engineering, process-oriented and multilingual research — and calls for a more theoretically grounded and methodologically diversified research agenda.

8

이용수:40회 영화 <기생충> 자막의 문화소 번역 연구

박건영, 남희지, 임소연

한국통역번역학회 통역과 번역 제23권 1호 2021.03 pp.27-56

※ 기관로그인 시 무료 이용이 가능합니다.

7,000원

This study examines the translation strategy of culturemes in the English subtitle of Parasite, a Korean movie by director Bong Joon-ho. The multi-award winning black comedy deals with the conflict between the rich and the poor, a topic which people in every culture can relate to. Together with the timely theme, the film’s English subtitle is considered to have contributed to its global success. This study shows that Darcy Paquet, the subtitle translator of Parasite, carefully chose the translation strategy working in close cooperation with the director. The interviews and press clips on the translator and the director revealed that they actively communicated on how to translate the local elements in the movie into English subtitle so that audiences in other cultures can easily understand the movie, which is the macro translation strategy. This paper categorized 22 culturemes in the movie into 5 groups and found out that 6 different tactics under 2 broad categories of conservation and substitution were used for translation. The analysis shows that although various tactics were used at the micro level, the subtitle as a whole worked in a way to enhance the understanding of foreign audiences, with the aim of domestication at the macro level.

9

이용수:39회 출판 번역 비평과 번역 규범

이상원

한국통역번역학회 통역과 번역 제6권 2호 2004.12 pp.39-57

※ 기관로그인 시 무료 이용이 가능합니다.

5,400원

This paper tries to analyse translation criticism on published books, using concept and sub-categories of translation norms. Analysed in this paper translation criticism divided into shcolars’ (but not in translation studies area) and general readers’. Translation norms as an analysing tool consist of 1) adequacy vs. acceptability, 2) translation policy, 3) directness 4) matricial norm 5) text-linguistic norm. Results are as follows: scholars’ criticism tends to focus on adequacy (accordance with source text culture), whereas general readers point out insufficient acceptability(accordance with source text culture); it seems that translation policy and directness are not the main concern in translation criticism; adequacy vs. acceptability norm is closely related with matricial and text-linguistic norm. The difference of scholars’ and general readers’ criticism tendency implies that different views possibly exist between various reader groups. This point needs further examination. Close relationship between adequacy vs. acceptability and matricial vs. text-linguistic norm also needs further research. The latter may be concrete basis for the former. It it is confirmed, we can make the analysing tool more simple. As for general readers, it is observed that readers, publishing companies and tranlators interact very actively on Internet sites. Although based on limited examples, this paper shows current state of translation criticism by Korean readers.

10

이용수:38회 AI 시대 전문 번역 교육에 대한 한영 번역 전공 교수자와 학습자의 인식 비교

이지은, 최효은

한국통역번역학회 통역과 번역 제27권 3호 2025.11 pp.171-211

※ 기관로그인 시 무료 이용이 가능합니다.

8,700원

The rapid advancement of AI and its expanding application in translation are bringing profound changes to translation education. However, the perspectives of instructors and learners, particularly those engaged in the professional translation training, remain underexplored in this shifting landscape. This qualitative study investigates their experiences in the evolving translation environment and their perceptions of translation education in the AI era through semi-structured interviews. The findings reveal that both groups acknowledge AI as a major force reshaping the field, while differing in their views on its implications for human translators and translator training. Learners tended to feel more intimidated by AI and often underestimated the human advantage in translation. Both groups, however, agreed that the ability to translate manually without AI support remains a fundamental prerequisite for translator training. Yet, they diverged in their views on pedagogy: Instructors emphasized text-based analysis supported by AI tools, whereas learners preferred more practical, hands-on training. This gap highlights the need for pedagogical models that integrate both perspectives, ensuring that translation education remains grounded in core translation skills while also reflecting learners’ demand for AI-supported practical training.

 
페이지 저장