챗GPT, 파파고, 인간 번역가 간의 한영 문학번역 차이점 연구
Differences in Korean-English literary translation among ChatGPT, Papago, and human translators
- 발행
- 2024
- 소속·발행
- 한국외국어대학교
- 출처
- 국내 KCI
- DOI
- 10.15749/jts.2024.25.2.001
- 원문등록
- 2024-06-29
- 원문
- 원문 보기 ↗
개념
키워드
챗GPT, NMT, 인간번역, 문학번역, 정량분석, ChatGPT, NMT, human translation, literary translation, quantitative analysis
초록
The present study explores stylistic and quality differences in English translations of a Korean short story by ChatGPT, Papago, and two human translators. Results of two types of quantitative analysis are reported. A PCA analysis showed that, in the distribution of 80 topmost frequent words, Papago was clearly distinguished from human translators while no such distinction was found vis-a-vis ChatGPT. In a follow-up manually-annotated creativity and quality analysis, Papago was again far from measuring up to human translators with near-zero creativity and numerous errors. ChatGPT also made many errors (about half of Papago’s) but exhibited a measure of creativity of the kinds seen in human translation. ChatGPT’s display of creativity, along with a significant reduction in errors compared to Papago, is attributed to ChatGPT’s ability to consider the context in comprehending the source text and transferring the meaning into the target language.