Earticle

초록

영어

This study examines the potential and limitations of generative AI in subtitle translation from the perspective of linguistic economy. It compares the official Korean subtitles of the Russian film with ChatGPT-generated translations produced under general and subtitle-specific prompts. A total of 663 subtitle segments were analyzed in terms of subtitle length and linguistic economy strategies. The results show that subtitle-specific prompts produced significantly shorter translations than general prompts, indicating that prompt design can improve linguistic economy to some extent. However, AI-generated subtitles remained significantly longer than the official subtitles and tended to retain the source-language sentence structure. Context-dependent strategies such as omission, sentence integration, and reduction of repetitive expressions were also less frequently observed in AI-generated subtitles. These findings suggest that generative AI has potential as a tool for subtitle drafting, but human intervention remains necessary to ensure readability, naturalness, and linguistic economy. This study provides empirical evidence of both the potential and limitations of generative AI in audiovisual translation.

목차

1. 서론
2. 이론적 배경
2.1. 생성형 AI의 발전과 번역 연구의 변화
2.2. 자막 번역의 특성과 언어의 경제성
2.3. 자막의 경제성 전략과 생성형 AI 번역의 평가 기준
3. 생성형 AI 기반 자막 번역의 언어의 경제성 분석
3.1. 분석 대상 및 방법
3.2. 정량 분석
3.3. 자막 길이의 변화
3.3.1. 음절 축소 전략
3.3.2. 전후 맥락을 고려한 생략
3.3.3. 문장 통합과 반복 표현 축약
3.3.4. 복합 전략
3.4. 소결
4. 결론
4.1. 연구의 의의
4.2. 향후 과제
참고문헌

키워드

저자

• 김규형 [ Kim, Kyuhyoung | 선문대학교 ]

참고문헌

발행기관

간행물

표지보기 관심저널 등록

• 간행물명

  통번역학연구 [Interpreting and Translation Studies]

• 간기

  계간

• pISSN

  1975-6321

• eISSN

  2713-8372

• 수록기간

  1997~2026

• 등재여부

  KCI 등재

• 십진분류

  KDC 717 DDC 400