International Journal of Advanced Culture Technology

The International Promotion Agency of Culture Technology (국제문화기술진흥원)
권호 표지
DOI QR코드

DOI QR Code

A Quality Comparison of English Translations of Korean Literature between Human Translation and Post-Editing

  • LEE, IL-JAE (Department of English Language and Literature, Kwangwoon University)
  • Received : 2018.11.22
  • Accepted : 2018.12.01
  • Published : 2018.12.31
Download PDF
⟨ Previous Next ⟩

Abstract

As the artificial intelligence (AI) plays a crucial role in machine translation (MT) which has loomed large as a new translation paradigm, concerns have also arisen if MT can produce a quality product as human translation (HT) can. In fact, several MT experimental studies report cases in which the MT product called post-editing (PE) as equally as HT or often superior ([1],[2],[6]). As motivated from those studies on translation quality between HT and PE, this study set up an experimental situation in which Korean literature was translated into English, comparatively, by 3 translators and 3 post-editors. Afterwards, a group of 3 other Koreans checked for accuracy of HT and PE; a group of 3 English native speakers scored for fluency of HT and PE. The findings are (1) HT took the translation time, at least, twice longer than PE. (2) Both HT and PE produced similar error types, and Mistranslation and Omission were the major errors for accuracy and Grammar for fluency. (3) HT turned to be inferior to PE for both accuracy and fluency.

Keywords

E1GMBY_2018_v6n4_165_f0001.png 이미지

Figure 1. Screenshot of VisualTran workbench

Table 1. Genre and source texts

E1GMBY_2018_v6n4_165_t0001.png 이미지

Table 2. Translator (HT) profiles

E1GMBY_2018_v6n4_165_t0002.png 이미지

Table 3. Post-editor (PE) profiles

E1GMBY_2018_v6n4_165_t0003.png 이미지

Table 4. Evaluation criteria

E1GMBY_2018_v6n4_165_t0004.png 이미지

Table 5: Accuracy evaluators

E1GMBY_2018_v6n4_165_t0005.png 이미지

Table 6. Fluency evaluators

E1GMBY_2018_v6n4_165_t0006.png 이미지

Table 7. Accuracy comparison of HT and PE

E1GMBY_2018_v6n4_165_t0007.png 이미지

Table 8. Fluency comparison of HT and PE

E1GMBY_2018_v6n4_165_t0008.png 이미지

References

  1. J. Daems, S. Vandepitte, R. Hartsuiker, and L. Macken, "Translation Methods and Experience: A Comparative Analysis of Human Translation and Post-editing with Students and Professional Translators," Meta: Journal des Traducteurs/Meta: Translators' Journal, Vol. 62, No. 2, pp. 245-270, 2017. https://doi.org/10.7202/1041023ar
  2. R. Fiederer and S. O'Brien, "Quality and Machine Translation: A Realistic Objective?" The Journal of Specialised Translation, Vol. 11, pp. 52-74, 2009.
  3. S.-H. Han, "Feature of CAT Tool-Based Collaborative Translations: Sentence Length and Cohesion," Interpreting and Translation Studies, Vol. 20, No. 4, pp. 167-188, 2016. (In Korean)
  4. ISO 18587:2017, Translation services - Post-editing of machine translation. Geneva: International Organization for Standardization, 2017.
  5. I. Lacruz, "Cognitive Effort in Translation, Editing, and Post-Editing," In J. W. Schwieter and A. Ferreira, eds., The Handbook of Translation and Cognition, pp. 386-401. New Jersey, USA: John Wiley & Sons, Inc., 2017.
  6. E. O'Curran, "Translation Quality in Post-Edited versus Human-Translated Segments: A Case Study," In S. O'Brien, M. Simard, and L. Specia, eds., Proceedings of the Third Workshop on Post-Editing Technology and Practice (WPTP-3), pp. 113-118, Vancouver, Canada, October 22-26, 2014.
  7. J.-Y. Park, "Language Technologies & the T&I Industry's Future," Interpreting and Translation Studies, Vol. 21, No. 1, pp. 137-168, 2017. (In Korean)
  8. M. Plitt and F. Masselot, "A Productivity Test of Statistical Machine Translation Post-Editing in a Typical Localisation Context," The Prague Bulletin of Mathematical Linguistics, Vol. 93, pp. 7-16, 2010.
  9. O. Temizoz, "Postediting Machine Translation Output: Subject-Matter Experts versus Professional Translators," Perspectives: Studies in Translatology, Vol. 24, No. 4, pp. 646-665, 2016. https://doi.org/10.1080/0907676X.2015.1119862