Earticle

초록

영어

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.

목차

Abstract
I. 들어가는 말
1. 연구 배경
2. 연구의 필요성
3. 연구의 목적
II. 이론적 배경
1. 기계번역 프로그램과 생성형 AI 기반 번역의 차이
2. 선행연구
III. 연구 방법론
1. 연구 설계
2. 분석 대상 번역 모델
3. 프롬프팅 유형별 번역 접근 방식
4. 분석용 데이터셋 구축 및 평가 방법
IV. 연구 분석 결과
1. 프롬프팅 유형별 번역 품질 비교
2. 언어쌍별 번역 품질 비교
3. 자동 프롬프트 최적화(APO) 적용 번역 효과 검증
4. 시사점
V. 결론 및 제언
1. 연구 결과 요약
2. 최적의 프롬프팅 전략 제안
3. 연구의 한계 및 향후 연구 방향
참고문헌

저자

• 곽은주 [ Kwak, Eun-joo | 세종대학교 ] 1저자
• 탁진영 [ Tak, Jin-young | 세종대학교 ] 공동저자
• 전현주 [ Chun, Hyunju | 신한대학교 ] 교신저자

참고문헌