원문정보
Generative AI and Machine Translation : A Study on Korean-Japanese Interpretation Education Through ChatGPT Translation.
초록
영어
With the popular uptake of ChatGPT, the interpreter community is set to undergo significant changes in its discussion and directions on topics related to machine translation. This study investigates the features and differences of ChatGPT, a natural language processing (NLP) tool, in comparison to Google Translate’s translation engine, specifically between the Korean and Japanese language pair, with the purpose of exploring means to leverage ChatGPT’s capabilities in the context of interpreter training in said pair. For this purpose, we will first analyze ChatGPT’s translation of idioms and proverbs to identify whether it is capable of paraphrasing polysemous connotations and implications. We will next analyze ChatGPT’s ability to translate unstructured colloquial utterances. Finally, we will analyze whether ChatGPT’s translation output displays translation universals such as simplification and clarification. Based on these analyses, this study will discuss how ChatGPT may be used toward interpreter training.
목차
1. 서론
2. 이론적 배경
2.1. 구글 번역과 챗GPT 번역
2.1.1. 구글 번역
2.1.2. 챗GPT 번역
2.2. 구어 텍스트로서의 통역
2.2.1. ‘구어 텍스트’와 ‘구어체化 텍스트’
2.2.2. 함축(implicature)
2.2.3. 번역 보편소
3. 분석 사례
3.1. 함축 번역
3.1.1. 함축(관용구)이 포함된 단문장 한일번역 비교
3.1.2. 함축(속담)이 포함된 단문장 한일번역 비교
3.1.3. 함축(속담)이 포함된 짧은 문장에 대한 한일번역 비교
3.2. 구어체化 텍스트 번역
3.3. 구어 텍스트 번역
3.3.1. 정리되지 않은 중간 길이의 발화 텍스트
3.3.2. 정리되지 않은 긴 길이의 발화 텍스트
4. 결론
참고문헌