본문 바로가기
  • Home

A Study on the Errors of Korean-Arabic Machine Translation in Literary Text—Focusing on Kim Ji-young, Born in 1982

  • The Journal of Translation Studies
  • Abbr : JTS
  • 2022, 23(3), pp.155-182
  • DOI : 10.15749/jts.2022.23.3.006
  • Publisher : The Korean Association for Translation Studies
  • Research Area : Humanities > Interpretation and Translation Studies
  • Received : August 7, 2022
  • Accepted : September 19, 2022
  • Published : September 30, 2022

Gwag, Soon-Lei 1

1한국외국어대학교

Accredited

ABSTRACT

This study aims to identify the availability and limitations of neural machine translation (NMT) through a comparative analysis of the Korean-Arabic human translation and NMT of a literary text. To this end, the NMT of Cho Nam-Joo’s novel Kim Ji-young, Born 1982 is analyzed compared to its human translation published in Arabic. Errors in the NMT output are classified into linguistic and cultural categories for quantitative analysis, and exemplary errors are qualitatively examined. According to the findings for the linguistic category, the meaning of words is almost accurately translated by NMT, but many errors involve polysemous words that must be translated according to their context. In particular, when negative words are included, the whole sentence is often translated into the opposite meaning. Many errors occur in the translation of pronouns as predicted. In the cultural category, abbreviations and food names are translated correctly in general, but the terms describing family relationships are translated into different meanings in many cases. Although this study uses limited data for analysis, it is meaningful in that it confirms the availability and limitations of Korean-Arabic NMT.

Citation status

* References for papers published after 2022 are currently being built.

This paper was written with support from the National Research Foundation of Korea.