심층학습을 이용한 기계번역 기술과 정확도 연구
A Study of Techniques and Accuracy of Machine Translation based on Deep Neural Network
2
조회
0
다운로드
10
인용
0
참고문헌
키워드
초록
In this study, we discuss the basic technology of machine learning of the deep neural network for natural language processing(NLP). We explain the distributed vector representation of words. Distributed vector representation is proved to be able to carry semantic meanings and are useful in various NLP tasks. The recurrent neural network(RNN) is employed to get the vector representation of sentences. We discuss the RNN encoder-decoder model and some modifications of the RNN structure to improve the accuracy of the machine translations. To test and verify the accuracy of Google translator, we performed the translation among Korean, English, and Japanese, and examined the meaning change between the original and the translated sentence. In neural network translation, we showed some inaccuracies of the translation such as wrong relation between subject and object, or some omission or repetition of the original meaning. In order to increase the performance and accuracy of machine translation, it is necessary to acquire more data for training.
Abstract
In this study, we discuss the basic technology of machine learning of the deep neural network for natural language processing(NLP). We explain the distributed vector representation of words. Distributed vector representation is proved to be able to carry semantic meanings and are useful in various NLP tasks. The recurrent neural network(RNN) is employed to get the vector representation of sentences. We discuss the RNN encoder-decoder model and some modifications of the RNN structure to improve the accuracy of the machine translations. To test and verify the accuracy of Google translator, we performed the translation among Korean, English, and Japanese, and examined the meaning change between the original and the translated sentence. In neural network translation, we showed some inaccuracies of the translation such as wrong relation between subject and object, or some omission or repetition of the original meaning. In order to increase the performance and accuracy of machine translation, it is necessary to acquire more data for training.
참고문헌 (12)
- 김희동, "인공지능과 인문학(언어학)", 국제언어인문학회 학술대회논문집 (2017), 국제언어인문학회
- 나승훈, "심층학습에 기반한 자연언어처리", 정보과학회지, pp.28~39 (2015), 한국정보과학회
- 박일섭, "기계번역의 발전과 한국어 교육 - 구글, 네이버의 신경망 번역시스템을 중심으로-", 제36차 전국학술대회 추계대회 논문집 (2017), 이중언어학회
- 박준석, "Analysis of the Types of Errors By the Google translator", 겨울언어학회학술대회 논문집 (2017), 한국언어학회
- Bojanowski, P., "Alternative Structures for Character-Level RNNs", arXiv:1511.06303, ~ (2015)
- Chung, J., "A Character-Level Decoder without Explicit Segmentation for Neural Machine Translation", arXiv:1603.06147, ~ (2016)
- Mikolov, T., "Distributed representations of words and phrases and their compositionality", Advances in Neural Information Processing Systems 26(NIPS 2013), pp.3111~3119 (2013)
- Quoc Le, "Distributed Representations of Sentences and Documents", Dwceedings of the 31st Internationl Conference on Machine Learning (2014)
- Yonghui Wu, "Google’s Neural Machine Translation System: Bridging the Gap between Human and Machine Translation", arXiv preprint arXiv:1609.081442v2, ~ (2016)
- Young, T., "Recent Trends in Deep Learning Based Natural Language Processing", arXiv preprint arXiv:1708.02709, ~ (2017)
- Yoav Goldberg, "A Primer on Neural Network Models for Natural Language Processing", Journal of Artificial Intelligence Research, 57, pp.345~420 (2016)
- Okazaki Naoaki, "自然言語処理におけるDeep Learning", 일본 전기전자정보통신학회 종합학술대회 논문집 (2017)