문학번역 적용을 위한 기계번역의 현주소
Current State of Machine Translation for Literary Translation Work
0
조회
0
다운로드
29
인용
0
참고문헌
키워드
초록
Along with the development of Neural Machine Translation (NMT), it has been predicted that machine translation can be used for various text types. However, predictions without objectives and scientific data are unreliable and even misleading. Hence, this paper tries to present an objective assessment of the current state of NMT and to investigate whether NMT can be applicable to Korean-to-English literary translation. The starting point is to step back from conventional mistranslation-centric approaches and to accommodate the findings both from natural language processing research and translation studies, since machine translation research is multidisciplinary in its nature. To that end, this paper introduces the structural limitations of NMT engines which have already been reported by engineering scholars, and tries to prove the limitations which cause distortion of the original meaning and literary effect. To build an objective data set, the machine translation outcomes from two free on-line translation engines were used to translate four Korean novels. Three of them were compared against human translation, segment by segment, to underline the difference and shortcomings of machine translation. In addition, machine translation outcomes of one novel, without matching human translation, were used just for data validation. Among the many constraints of NMT, this paper selected and focused on unpredictable omission, difficulty in reading the context, long sentence processing, and out-of-vocabulary processing. After reviewing all these drawbacks, this paper makes some suggestions as to how we should view machine translation as a potential tool for future literary translation.
Abstract
Along with the development of Neural Machine Translation (NMT), it has been predicted that machine translation can be used for various text types. However, predictions without objectives and scientific data are unreliable and even misleading. Hence, this paper tries to present an objective assessment of the current state of NMT and to investigate whether NMT can be applicable to Korean-to-English literary translation. The starting point is to step back from conventional mistranslation-centric approaches and to accommodate the findings both from natural language processing research and translation studies, since machine translation research is multidisciplinary in its nature. To that end, this paper introduces the structural limitations of NMT engines which have already been reported by engineering scholars, and tries to prove the limitations which cause distortion of the original meaning and literary effect. To build an objective data set, the machine translation outcomes from two free on-line translation engines were used to translate four Korean novels. Three of them were compared against human translation, segment by segment, to underline the difference and shortcomings of machine translation. In addition, machine translation outcomes of one novel, without matching human translation, were used just for data validation. Among the many constraints of NMT, this paper selected and focused on unpredictable omission, difficulty in reading the context, long sentence processing, and out-of-vocabulary processing. After reviewing all these drawbacks, this paper makes some suggestions as to how we should view machine translation as a potential tool for future literary translation.
참고문헌 (36)
- 김도훈, "문화소 번역에서의 인지적 축적물의 역할 및 번역전략", 통역과 번역, 8(2), pp.3~29 (2006), 한국통역번역학회
- 김유섭, "기계 번역에서의 평가인공신경망 방식의 기계번역 시대의 서막", ITRI 국제컨퍼런스 발표집, pp.337~357 (2018)
- 김준석, "인공신경망 방식의 기계번역 시대의 서막", 한국통역번역학회 발표집, pp.14~30 (2017)
- 마승혜, "기계화되기 어려운 인간 능력과 문학번역 능력 비교․고찰 및 논의", 통번역학연구, 21(3), pp.55~77 (2017), 통번역연구소[DOI]
- 마승혜, "문학작품 기계번역의 한계에 대한 상세 고찰", 통번역학연구, 22(3), pp.65~88 (2018), 통번역연구소[DOI]
- 설명 가능한 AI 기술을 포함한 인공지능의 IP-R&D 전략, "윤태승", 정보통신기술진흥센터, 2~13 (2018)
- 송연석, "기계번역 담론에 대한 비판적 고찰", 번역학연구, 19(1), pp.119~145 (2018), 한국번역학회[DOI]
- 이상빈, "트랜스크리에이션, 기계번역, 번역교육의 미래", 통역과 번역, 18(2), pp.129~152 (2016), 한국통역번역학회[DOI]
- 이은숙, "텍스트 유형에 따른 인칭대명사 번역연구", 영어영문학연구, 54(3), pp.307~325 (2012), 한국중앙영어영문학회[DOI]
- 이홍식, "고유명사의 의미와 지시에 대하여", 한국학연구, (40), pp.307~334 (2016), 한국학연구소
- 이현경, "인공지능이 우리 아이들을 웃긴다", ITRI학술대회 발표집, pp.181~192 (2018)
- 장석원, "산문(散文)의 리듬에 대한 시론(試論) - 4⋅19의 리듬 -", 한국근대문학연구, (30), pp.41~66 (2014), 한국근대문학회
- 최윤영, "기계번역과 문학번역", 번역연구, 4, pp.51~61 (1996)
- 홍문표, "한-독 대화체 기계번역을 위한 주어생략현상의 처리방안", 독어학, (24), pp.417~439 (2011), 한국독어학회[DOI]
- Bassnett, S, "Oxford Handbooks Online", ~ (2011)
- Bentivogli, L., "Neural versus phrase-based mt quality : An in-depth analysis on english-german and english-french", Computer Speech & Language, 49, pp.52~70 (2018)
- Besacier, L., "Automated translation of a literary work: a pilot study", Proceedings of the Fourth Workshop on Computational Linguistics for Literature, pp.114~122 (2015)
- Castilho, S., "Is neural machine translation the new state of the art?", The Prague Bulletin of Mathematical Linguistics, 108(1), pp.109~120 (2017)
- Choi, H., "Context-dependent word representation for neural machine translation", Computer Speech & Language, 45, pp.149~160 (2017)
- Davies, E., "Leaving it out : On some justifications for the use of omission in translation", Babel, 53(1), pp.56~77 (2007)
- Gambier, Y., "Translation strategies and tactics", Handbook of translation studies, 1, pp.412~418 (2010)
- Goebel, R., "Explainable AI: the new 42?", International Cross-Domain Conference for Machine Learning and Knowledge Extraction, pp.295~303 (2018)
- Hutchins, J., "Current commercial machine translation systems and computer-based translation tools: system types and their uses", International Journal of Translation, 17(1-2), pp.5~38 (2005)
- Kuang, S., "Automatic long sentence segmentation for neural machine translation", Natural Language Understanding and Intelligent Applications, pp.162~174 (2016)
- Luong, M., "Addressing the rare word problem in neural machine translation" (2014)
- Nord, C., "Text analysis in translation: Theory, methodology, and didactic application of a model for translation-oriented text analysis (No. 94)" (2005), Rodopi
- Papineni, K., "BLEU: a method for automatic evaluation of machine translation", Proceedings of the 40th annual meeting on association for computational linguistics, pp.311~318 (2002)
- Pouget-Abadie, J., "Overcoming the curse of sentence length for neural machine translation using automatic segmentation" (2014)
- Reiss, K., "Towards a general theory of translational action: Skopos theory explained" (2014), Routledge
- Su, J., "A Hierarchy-to-Sequence Attentional Neural Machine Translation Model", IEEE, 2018, pp.26(3), 623~632
- Toral, A., "Machine-assisted translation of literary text : A case study", Translation Spaces, 4(2), pp.240~267 (2015)
- Toral, A., "What level of quality can neural machine translation attain on literary text?" (2018)
- Voigt, R., "Towards a literary machine translation: The role of referential cohesion", Proceedings of the NAACL-HLT 2012 Workshop on Computational Linguistics for Literature, pp.18~25 (2012)
- Voita, E., "Context-Aware Neural Machine Translation Learns Anaphora Resolution" (2018)
- Wang, T., "Text Simplification Using Neural Machine Translation", AAAI, pp.4270~4271 (2016)
- Wu, Y., "Google's neural machine translation system: Bridging the gap between human and machine translation" (2016)