인공신경망 기계 번역의 한일/일한 번역 품질에 대한 예비연구-품질향상 검토와 교열코드 적용-
Quality of neural machine translation for the Korean-Japanese language pair- the development of editing codes for machine translation
0
조회
0
다운로드
41
인용
0
참고문헌
키워드
초록
At the present time, when the development of neural machine translation presents a significant turning point, this paper attempts to compare NMT with existing statistically-based machine translation, and discuss implications for future translator education. Multiple types of MT errors and mistranslations are identified by analysis. This study intends to propose a codified table of those error types as a tool for objective assessment and ongoing monitoring of the quality of MT. Based on a translation editing scheme for learners, error types at lexical, phrasal, syntactic and textual levels were identified, which were then re-sorted for MT. The classification was applied to the analysis of translation of informative texts and news articles, for different error types, MT platforms (Naver, Google) and language directions, to draw graphs to demonstrate the results. Considering that the work of translation in the future will likely evolve into a combination of MT with human post-editing, continuous MT quality assessment would be necessary. The outcome of this study would help post-editors figure out where to focus working with different MT platforms, which is potentially useful for translator training.
Abstract
At the present time, when the development of neural machine translation presents a significant turning point, this paper attempts to compare NMT with existing statistically-based machine translation, and discuss implications for future translator education. Multiple types of MT errors and mistranslations are identified by analysis. This study intends to propose a codified table of those error types as a tool for objective assessment and ongoing monitoring of the quality of MT. Based on a translation editing scheme for learners, error types at lexical, phrasal, syntactic and textual levels were identified, which were then re-sorted for MT. The classification was applied to the analysis of translation of informative texts and news articles, for different error types, MT platforms (Naver, Google) and language directions, to draw graphs to demonstrate the results. Considering that the work of translation in the future will likely evolve into a combination of MT with human post-editing, continuous MT quality assessment would be necessary. The outcome of this study would help post-editors figure out where to focus working with different MT platforms, which is potentially useful for translator training.
참고문헌 (20)
- 김순미, "신경망번역기(NMT) 활용 학부 번역교육의 가능성 연구", 통번역교육연구, 15(3), pp.5~37 (2017), 한국통번역교육학회[DOI]
- 김종희, "포털사이트(portal site) 번역기의 오역에 관한 연구 - 정보 및 설명 텍스트를 중심으로 -", 일어일문학, (69), pp.141~158 (2016), 대한일어일문학회[DOI]
- 마승혜, "기계화되기 어려운 인간 능력과 문학번역 능력 비교․고찰 및 논의", 통번역학연구, 21(3), pp.55~77 (2017), 통번역연구소[DOI]
- 박순애, "일・한기계번역과 일본어교육", 일본어문학, (67), pp.97~122 (2014), 일본어문학회[DOI]
- 박영란, "영한번역에서의 시제의 등가성과 기계번역과의 비교: 영어 현재진행형을 중심으로", 통번역교육연구, 15(1), pp.165~194 (2017), 한국통번역교육학회[DOI]
- 박준석, "Analysis of the Types of Translation Errors by the Google Translator", 영어영문학연구, 59(4), pp.279~299 (2017), 한국중앙영어영문학회[DOI]
- 박지영, "언어 기술 혁신과 통번역 산업의 미래: 20대 글로벌 LSP의 통번역 서비스 분석을 바탕으로", 통번역학연구, 21(1), pp.137~168 (2017), 통번역연구소[DOI]
- 신경미, "중국어 자동 번역 시스템 현황과 시스템 구축을 위한 제안", 한중인문학연구, (56), pp.199~219 (2017), 한중인문학회[DOI]
- 신지선, "인공지능 번역 시스템의 출현에 대한 소고", 번역학연구, 18(5), pp.91~110 (2017), 한국번역학회[DOI]
- 이주리애, "인공신경망 기계 번역의 한일", 일한 번역 품질 고찰-구글과 네이버를 중심으로-, 2018, 209~213
- 이하자, "한·일 기계번역시스템의 문제점 고찰 ― 번역가 번역문과의 대조분석을 통해 ―", 日本語敎育, (58), pp.151~166 (2011), 한국일본어교육학회
- 임순정, "구글 번역의 사례연구: 번역품질과 번역단위와의 관계를 중심으로", 번역학연구, 15(1), pp.177~209 (2014), 한국번역학회[DOI]
- 장애리, "국내 기계 통번역의 발전 현황 분석: 한·중 언어 쌍을 중심으로", 번역학연구, 18(2), pp.171~206 (2017), 한국번역학회[DOI]
- 조정현, "BLEU 를 활용한 단기 서술형 답안의 자동채점", 한국 HCI 학회 학술대회, pp.606~610 (2009)
- 한승희, "기계번역·인간번역·트랜스크리에이션의 문체 비교: 광고 번역을 중심으로", 통번역학연구, 21(2), pp.163~188 (2017), 통번역연구소[DOI]
- 豊島知穂, "校閲カテゴリ体系に基づく翻訳学習者の誤り傾向の分析", 通訳翻訳研究への招待, 16, pp.47~65 (2016)
- モリセイ·ケビン, "日英技術翻訳におけるエラーの分析, および分析結果に基づいた技術翻訳評価システムの開発", 情報処理学会研究報告デジタルドキュメント, pp.1~8 (2007)
- Reiss, K., "Text types, translation types and translation assessment", pp.105~115 (1989), Lebende Sprachen