Article published In: APTIF 9 - Reality vs. Illusion: From Morse code to machine translation
Edited by Frans De Laet, In-kyoung Ahn and Joong-chol Kwak
[Babel 66:4/5] 2020
► pp. 811–828
Defining language dependent post-editing guidelines for specific content
The case of the English-Korean pair to improve literature machine translation styles
Published online: 21 July 2020
https://doi.org/10.1075/babel.00174.mah
https://doi.org/10.1075/babel.00174.mah
Abstract
The rapid development of neural machine translation systems and the emergence of the e-book have broadened the
scope of text types that can be translated by machines. At the early stage of the machine’s infiltration into the translation
field, target texts were mainly technical texts such as patents, instruction manuals, etc. Literary texts have been considered as
the last bastion of human translation because the machine translation (MT) has produced word-for-word translation, unsuitable for
literary texts with distinct stylistic elements. However, it turns out that the field of literary translation was not immune to
the rise of MT. Style is one of the critical elements in literary texts, but it has been dismissed in the existing MT post-editing
guidelines. Therefore, this research attempts to provide methodological ideas about how to come up with a machine translation
post-editing guideline (MTPE) for style improvement especially for language pairs with divergent syntax and semantics like English
and Korean. First, the linguistic and cultural differences in writing styles are sorted out based on previous research. Second,
the different ways in which human translators address writing style are investigated. Third, the strategies that human translators
employ in their translations are applied to machine translation post-editing to demonstrate how the strategies can be incorporated
into English-Korean MTPE to improve style. This preliminary research would lay the groundwork for refining post-editing style
guidelines and for accumulating manually post-edited data for style improvement, which would be conducive to building and
customizing automatic post-editing systems.
Résumé
Le développement rapide des systèmes de traduction automatique neuronale et l’émergence du livre
électronique ont élargi la portée des types de textes pouvant être traduits par des machines. Lorsque la machine a commencé de
s’implanter dans le secteur de la traduction, les textes cibles étaient principalement des textes techniques, tels que des
brevets, manuels d’instruction, etc. Les textes littéraires étaient considérés comme le dernier bastion de la traduction humaine,
parce que la traduction automatique (TA) produisait une traduction littérale, inadaptée à des textes littéraires, caractérisés par
des éléments stylistiques propres. Cependant, il s’avère que le domaine de la traduction littéraire n’a pas été épargné par
l’essor de la TA. Bien que le style constitue l’un des éléments déterminants dans les textes littéraires, on l’a exclu des
directives actuelles de post-édition de TA. C’est pourquoi cette recherche tente d’avancer des pistes méthodologiques sur la
manière d’élaborer une directive en matière de post-édition de traduction automatique (PETA), afin d’améliorer le style, en
particulier dans des combinaisons linguistiques dont la syntaxe et la sémantique diffèrent, comme l’anglais et le coréen. Primo,
les différences linguistiques et culturelles dans les styles d’écriture ont été triées sur la base de recherches antérieures.
Secundo, les différentes manières dont les traducteurs humains abordent le style d’écriture ont été examinées. Tertio, les
stratégies qu’utilisent les traducteurs humains dans leurs traductions ont été appliquées à la post-édition de traduction
automatique, pour démontrer comment on peut les intégrer dans la PETA de l’anglais en coréen, afin d’améliorer le style. Cette
recherche préliminaire pourrait être à la base d’une amélioration des directives stylistiques en post-édition et d’une
accumulation de données post-éditées manuellement dans l’objectif d’améliorer le style. Cela pourrait favoriser l’élaboration et
la personnalisation des systèmes de post-édition automatique.
Article outline
- 1.Introduction
- 2.Theoretical background
- 2.1Literary text machine translation
- 2.2The necessity of establishing a style guidelinein literary text machine translation
- 3.Method
- 3.1Linguistic and cultural differences in language usebetween English and Korean
- 3.2Human translators’ strategies for style improvement
- 3.2.1Inserting onomatopoeia and mimetic words
- 3.2.2Inserting intensifiers
- 3.3Application to machine translation post-editing
- 3.3.1Inserting mimetic words to MTs from English to Korean
- 3.3.2Inserting intensifiers to MTs from Korean to English
- 4.Discussions and limitations
- 5.Conclusion
- Notes
References
References (30)
Densmer, Lee. 2014. “Light and Full MT Post-editing Explained”. [URL]
Fallon, Claire. 2015. “This Shocking Book Cover Sums Up The Sneaky Sexism Of Literary Publishing”. [URL]
Flanagan, Marian; and Tina Paulsen Christensen. 2014. “Testing Post-editing Guidelines: How Translation Trainees Interpret Them and How to Tailor Them for Translator Training Purposes”. The Interpreter and Translator Trainer 8 (2): 257–275.
Hara, Kazuya; and Min-Sun Kim. 2004. “The Effect of Self-Construals on Conversational Indirectness”. International Journal of Intercultural Relations 28 (1): 1–18.
Hu, Ke; and Patrick Cadwell. 2016. “A Comparative Study of Post-editing Guidelines”. Baltic J. Modern Computing 4 (2): 346–353.
Jones, Ruth; and Ann Irvine. 2013. “The (Un)faithful Machine Translator”. In Proceedings of the 7th Workshop on Language Technology for Cultural Heritage, Social Sciences, and Humanities, 96–101. Association for Computational Linguistics.
Kim, Do-Hun. 2014. “Comparison between Korean-English Onomatopoeia and Translation of Korean Onomatopoeia into English”. The Journal of Translation Studies 15 (1): 25–50.
Kim, Heejung S.; and David K. Sheman. 2007. “Express Yourself: Culture and the Effect of Self-Expression on Choice”. Journal of Personality and Social Psychology 921: 1–11.
Koglin, Arlene. 2015. “An Empirical Investigation of Cognitive Effort Required to Post-edit Machine Translated Metaphors Compared to the Translation of Metaphors”. Translation & Interpreting 7 (1): 126–143.
Lee, Chang-Soo. 2007. “An Analysis of the Functional Effectiveness of Translated English Tourist Information Texts”. Conference Interpretation and Translation 9 (2): 155–180.
Mah, Seung-Hye. 2016. “A Case Study of a Communicative Literary Translation and its Pedagogical Implications”. Interpretation and Translation 18 (1): 47–74.
Mesa-Lao, Bartolomé. 2013. “Introduction to Post-editing-The CasMaCat GUI”. [URL]
Noh, Jinseo. 2008. “Onomatopoeia in Korean-English Translation of Poetic Phrases and Translation Strategies”. Conference Interpretation and Translation 10 (1): 45–63.
O’Brien, Sharon. 2010. “Introduction to Post-Editing: Who, What, How and Where to Next?” [URL]
Pérez, Celia Rico. 2012. “A Flexible Decision Tool for Implementing Post-editing guidelines”. Localisation Focus 11 (1): 54–66.
Shin, Jungho. 2012. A Comparative Study of Symbolic words in Japanese and Korean. MA thesis. Oslo: University of Oslo.
Schourup, Lawrence. 1993. “Contrastive Study of Japanese and English Onomatopoeia”. Gengo 22 (6): 48–55.
TAUS. 2016. “TAUS Post-editing Guidelines”. [URL]
Toral, Antonio; and Victor M. Sánchez-Cartagena. 2017. “A Multifaceted Evaluation of Neural versus Phrase-based Machine Translation for 9 Language Directions”. In Proceedings of the 15th Conference of the European Chapter of the Association for Computational Linguistics: Vol. 1, 1063–1073. Valencia: Long Papers.
Toral, Antonio; and Andy Way. 2015a. “Machine-assisted Translation of Literary Text: A Case Study”. Translation Spaces 4 (2): 240–267.
. 2015b. “Translating Literary Text between Related Languages using SMT”. In Proceedings of NAACL-HLT Fourth Workshop on Computational Linguistics for Literature, 123–132. Denver (CO).
. 2018. “What Level of Quality Can Neural Machine Translation Attain on Literary Text?” In Translation Quality Assessment: From Principles to Practice, ed. by Joss Moorkens; Sheila Castilho; Federico Gaspari; and Stephen Doherty, 263–287. Heidelberg: Springer.
Yoon, Miseon; Kim, Take-Min; Lim, Jinju; and Seung-Yeun Hong. 2018. “Post-editing Guidelines for English-Korean Language Pairs: Guidelines and Examples for Future Post-editors”. The Journal of Translation Studies 19 (5): 43–76.
Vaid, Jyotsna; Choi, Hyun; Chen, Hsin-Chin; and Michael Friedman. 2008. “Perceiving and Responding to Embarrassing Predicaments across Languages”. The Mental Lexicon 3 (1): 121–147.
Cited by (4)
Cited by four other publications
Chen, Shiyue & Yan Lin
Gülmüş Sırkıntı, Halise
Hongtao, Wang
2023. Defending the last bastion. Babel. Revue internationale de la traduction / International Journal of Translation
Rico, Celia
2022. Mind the gap. Babel. Revue internationale de la traduction / International Journal of Translation 68:5 ► pp. 697 ff.
This list is based on CrossRef data as of 2 december 2025. Please note that it may not be complete. Sources presented here have been supplied by the respective publishers. Any errors therein should be reported to them.
