지원사업
학술연구/단체지원/교육 등 연구자 활동을 지속하도록 DBpia가 지원하고 있어요.
커뮤니티
연구자들이 자신의 연구와 전문성을 널리 알리고, 새로운 협력의 기회를 만들 수 있는 네트워킹 공간이에요.
논문 기본 정보
- 자료유형
- 학술저널
- 저자정보
- 저널정보
- 한국통계학회 CSAM(Communications for Statistical Applications and Methods) CSAM(Communications for Statistical Applications and Methods) 제27권 제3호
- 발행연도
- 2020.5
- 수록면
- 313 - 326 (14page)
이용수
초록· 키워드
오류제보하기
Deep Learning is the most important key to the development of Artificial Intelligence (AI). There are several distinguishable architectures of neural networks such as MLP, CNN, and RNN. Among them, we try to understand one of the main architectures called Recurrent Neural Network (RNN) that differs from other networks in handling sequential data, including time series and texts. As one of the main tasks recently in Natural Language Processing (NLP), we consider Neural Machine Translation (NMT) using RNNs. We also summarize fundamental structures of the recurrent networks, and some topics of representing natural words to reasonable numeric vectors.We organize topics to understand estimation procedures from representing input source sequences to predict target translated sequences. In addition, we apply multiple translation models with Gated Recurrent Unites (GRUs) in Keras on English-Korean sentences that contain about 26,000 pairwise sequences in total from two different corpora, colloquialism and news. We verified some crucial factors that influence the quality of training. We found that loss decreases with more recurrent dimensions and using bidirectional RNN in the encoder when dealing with short sequences. We also computed BLEU scores which are the main measures of the translation performance, and compared them with the score from Google Translate using the same test sentences. We sum up some difficulties when training a proper translation model as well as dealing with Korean language. The use of Keras in Python for overall tasks from processing raw texts to evaluating the translation model also allows us to include some useful functions and vocabulary libraries as well.
목차
Abstract
1. Introduction
2. Concepts in neural machine translation with recurrent neural network
3. Case study: English-Korean corpora
4. Conclusion
References
참고문헌 (0)
참고문헌 신청함께 읽어보면 좋을 논문
논문 유사도에 따라 DBpia 가 추천하는 논문입니다. 함께 보면 좋을 연관 논문을 확인해보세요!
-
분류와 예측에 기반한 자기상관 공정 모니터링 절차의 성능 비교
한국데이터정보과학회지
2023 .09
-
Introduction to convolutional neural network using Keras; an understanding from a statistician
CSAM(Communications for Statistical Applications and Methods)
2019 .11
-
Two-dimensional attention-based multi-input LSTM for time series prediction
CSAM(Communications for Statistical Applications and Methods)
2021 .01
-
Recurrent neural network model for bidirectional associative memory
Proceedings of the Jangjeon Mathematical Society
2018 .01
-
Predicting Bitcoin Market Trend with Deep Learning Models
Quantitative Bio-Science
2018 .05
-
심층신경망으로 가는 통계 여행, 두 번째 여행: RNN의 구조와 이미지 분류
응용통계연구
2024 .10
-
순환신경망 모형을 활용한 시계열 비교예측
Journal of The Korean Data Analysis Society
2019 .01
-
순환신경망을 이용한 질병발생건수 예측
응용통계연구
2020 .10
-
딥러닝 기반 LSTM 모형에 기초한 자기상관 공정의 모니터링 절차
한국데이터정보과학회지
2022 .03
-
Applying deep recurrent neural networks for Hourly Multi-step Multi-site Rainfall Forecasting: A use-case of Gangwon Province, Korea
한국기상학회 학술대회 논문집
2019 .10
-
Hyper Parameter Tunning을 통한 RNN 기반 모델의 PM2.5 예측 성능 비교
한국대기환경학회 학술대회논문집
2022 .10
-
Recurrent neural network-adapted nonlinear ARMA-GARCH model with application to S&P 500 index data
한국데이터정보과학회지
2019 .09
-
기계 번역과 자연어처리를 활용한 튜터링 활동 분석
Journal of The Korean Data Analysis Society
2023 .02
-
SHORT NOTE ON THE BEHAVIOR OF RECURRENT NEURAL NETWORK FOR NOISY DYNAMICAL SYSTEM
JOURNAL OF THE KOREAN SOCIETY FOR INDUSTRIAL AND APPLIED MATHEMATICS
2024 .12
-
Biharmonic hypersurfaces with recurrent operators in the Euclidean space
대한수학회보
2022 .11
-
The roles of differencing and dimension reduction in machine learning forecasting of employment level using the FRED big data
CSAM(Communications for Statistical Applications and Methods)
2019 .09
-
다중 시계열을 이용한 장기 예측 Transformer 모델
응용통계연구
2024 .10
-
Analysis of bivariate recurrent event data with zero inflation
CSAM(Communications for Statistical Applications and Methods)
2020 .01
-
IPCC 종합 보고서의 정책 결정자를 위한 요약 원본과 한국어 번역본의 ‘과학적 불확실성과 저자 입장’ 표현 비교 분석
한국기후변화학회지
2024 .10
-
RECURRENCE AND STABILITY OF POINTS IN DISCRETE FLOWS
Journal of applied mathematics & informatics
2019 .01
이 논문의 저자 정보
최근 본 자료
댓글(0)
0
UCI(KEPA) : I410-ECN-0101-2023-310-001442009