영어자원문법을 활용한 신경망 기계번역의 데이터 증강과 성능 평가 = Evaluation of Neural Machine Translation Trained by Augmented Data Using English Resource Grammar

다국어 초록 (Multilingual Abstract)

Machine translation commonly involves both analysis and generation across different human languages. This implies that parallel corpora of a large size are essential to create a theoretically reliable and practically robust translation model. However, as is well known, the parallel corpora between Korean and English are insufficient. In this respect, this study expands the data by means of English Resource Grammar (Flickinger 2000) to improve the translation model between the languages. Then, it looks at whether the neural machine translation model performs better with the augmented data. Unfortunately, it turns out the translation models based on augmented data exhibit rather lower BLEU scores. This study further discusses the reason for the unsatisfactory scores and raises the necessity of human evaluation as a next step.

참고문헌 (Reference)

1 허광호, "신경망 기반 기계 번역을 위한 역-번역을 이용한 한영 병렬 코퍼스 확장" 언어공학연구회 470-473, 2018

2 박찬준, "공공 한영 병렬 말뭉치를 이용한 기계번역 성능 향상 연구" 한국디지털정책학회 18 (18): 271-277, 2020

3 Koehn, P., "Statistical machine translation" Cambridge University Press 2009

4 Koehn, P., "Six challenges for neural machine translation" 28-39, 2017

5 Callison-Burch, C., "Re-evaluating the role of BLEU in machine translation research" 249-256, 2006

6 Callmeier, U., "Preprocessing and encoding techniques in PET" Collaborative Language Engineering 127-143, 2002

7 Nichols, E., "Paraphrasing training data for statistical machine translation" 5 (5): 950-971, 2010

8 Klein, G., "Opennmt : Open-source toolkit for neural machine translation" 67-72, 2017

9 Flickinger, D., "On building a more efficient grammar by exploiting types" 6 (6): 15-28, 2000

10 Sennrich, R., "Neural machine translation of rare words with subword units" 1717-1725, 2015

11 Bahdanau, D., "Neural machine translation by jointly learning to align and translate" 2014

12 Copestake, A., "Minimal recursion semantics: An introduction" 3 (3): 281-332, 2005

13 Cho, K., "Learning phrase representations using RNN encoder-decoder for statistical machine translation" 1724-1734, 2014

14 Carpuat, M., "Improving statistical machine translation using word sense disambiguation" 61-72, 2007

15 Sennrich, R., "Improving neural machine translation models with monolingual data" 86-96, 2015

16 Copestake, A., "Implementing typed feature structure grammars(Vol. 110)" CSLI publications 2002

17 Andreas, J., "How much do word embeddings encode about syntax?" 2 : 822-827, 2014

18 Chiang, D., "Hierarchical phrase-based translation" 33 (33): 201-228, 2007

19 Elman, J. L., "Finding structure in time" 14 (14): 179-211, 1990

20 Mikolov, T., "Efficient estimation of word representations in vector space" 1-12, 2013

21 Madabushi, H. T., "CxGBERT : BERT meets Construction Grammar" 4020-4032, 2020

22 Papineni, K., "Bleu: a method for automatic evaluation of machine translation" 311-318, 2002

23 Vaswani, A., "Attention is all you need" 5998-6008, 2017

24 Yamada, K., "A syntax-based statistical translation model" 523-530, 2001