韓日AI翻訳の自動評価と翻訳テクニック分析 - 人手翻訳との比較を通して -
Automatic Evaluation and Translation Techniques in Korean–Japanese AI Translation - A Comparative Study with Human Translation -
The present study aims to compare the translation quality of human translation and AI translation-specifically neural machine translation (NMT) and large language model (LLM)-based translation—in the context of Korean–Japanese translation. The source texts comprised informative texts (news articles) and expressive texts (columns), while the target texts included professional human translations as well as AI translations generated by Google, Papago, DeepL, and ChatGPT in 2023 and 2025. Translation quality was assessed using BLEU and TER metrics computed with SacreBLEU to ensure reproducibility, and complemented by a qualitative analysis employing Molina & Hurtado Albir’s(2002)translation techniques at the sentence level. The results revealed that DeepL achieved the highest BLEU and TER scores, whereas ChatGPT employed a broader range of techniques and produced translations most comparable to human translations. These findings highlight the limitations of automatic metrics and demonstrate the importance of combining quantitative metrics with qualitative and human evaluation to achieve a more comprehensive understanding of AI translation performance.
한국일본언어문화학회 [Japanese Language & Culture Association of Korea]
설립연도
2001
분야
인문학>일본어와문학
소개
본 학회는 일본어학 및 일본문학은 물론, 일본의 정치, 경제, 문화, 사회 등의 일본학 전반에 걸친 연구 및 일본의 언어, 문화를 매체로 한 한국과의 비교 연구를 대상으로 하고 있다. 본 학회는 회원들에게 연구 발표 및 정보 교환의 기회를 부여하고 나아가 한국에서의 바람직한 일본 연구 자세를 확립하는 것을 주된 목표로 하고 있다.