기계 번역 결과물 평가에 있어서 응결성 도입 가능성 고찰: 구글번역, 딥엘(DeepL), 챗지피티(ChatGPT) 번역의 코메트릭스(Coh-Metrix) 분석을 중심으로
Exploring the feasibility of incorporating cohesion in machine translation evaluation: A Coh-Metrix analysis of Google Translate, DeepL, and ChatGPT translations
- 발행
- 2025 등록이 논문은 발행 시점을 확인하지 못해 원문 등록일을 적었습니다. KCI가 2005~2008년에 옛 논문을 몰아서 올린 탓에, 그 시기 등록분은 발행보다 평균 3~5년 늦습니다. 실제 발행연도는 더 이를 수 있습니다.
- 소속·발행
- 이화여자대학교
- 출처
- 국내 KCI
- 원문
- 원문 보기 ↗
개념
키워드
machine translation, ChatGPT, quality assessment, cohesion, coh-metrix, machine translation, ChatGPT, quality assessment, cohesion, coh-metrix
초록
This study explores the feasibility of incorporating cohesion as an evaluation criterion beyond the sentence level in machine translation assessment. To this end, the study employed Coh-Metrix to measure the cohesion of English translations produced by Google Translate, DeepL, and ChatGPT for 68 Korean editorials, focusing on three criteria: pronouns, connectives, and repetition. One-way ANOVA and Tukey’s HSD test were conducted to determine whether there were significant differences in cohesion among the machine translation engines. The results revealed differences in content word overlap, latent semantic cohesion between adjacent sentences, and the distribution of given and new information across translation outputs. Additionally, variations were observed in the frequency of temporal and additive connectives, as well as in the occurrence of first-person singular and plural pronouns. A detailed analysis of cases with significant differences showed that, while individual sentences may appear accurate, the translations sometimes failed to convey the original meaning accurately within a larger context, potentially hindering reader comprehension. This study is significant in that it m