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
- 학위논문
- 저자정보
- 지도교수
- 손경아
- 발행연도
- 2017
- 저작권
- 아주대학교 논문은 저작권에 의해 보호받습니다.
이용수4
이 논문의 연구 히스토리 (2)
- 이 논문의 후속연구가 궁금하신가요?
- 연관 학술논문 또는 학술발표를 통해 보다 발전된 연구결과를 확인하실 수 있습니다.
- 이 논문의 연구 히스토리 확인하기
초록· 키워드
오류제보하기
Most successful neural language modeling have mainly focused on English language and operated at the level of words. Although word-level based neural language model performs well, some other languages cannot get word-level token easily especially in Korean language model. In the field of natural language processing for the Korean language, morpheme-level approaches are commonly employed as alternatives to the word in English. However, it causes the dependency to the external morphology analyzer. Accordingly, character-level approaches are preferred for Korean neural language modeling, but there are several ways to represent the Korean language in character-level, as which we call them Korean-letter level and Korean-grapheme level representations. In this thesis, we investigate the best representations of the Korean language with evaluation on three experiments: reconstruction, marker classification, and spelling correction. Since there are no public datasets in the Korean language for the three tasks, we first generate the datasets using a Korean public corpus. Furthermore, we propose an advanced architecture which can effectively employ various representations for sequence-to-sequence problem in the Korean language. In our experiments, we showed that the proposed architecture outperforms the traditional architectures that use only one of the representations.
목차
I. Introduction 1A. Background 1B. Research Objectives 2C. Thesis organizations 3II. Related Works 4A. English word level neural language modeling 4B. English character level neural language modeling 4C. Korean morpheme level neural language modeling 5D. Korean character level neural language modeling 5III. Methods 7A. Data Set: Sejong Corpus with Colloquial Style 7１. Marker classification datasets generated from Sejong Corpus 11２. Spelling correction datasets generated from Sejong Corpus 12B. Encoder-Decoder Model 14１. Sequence-to-Sequence Problem 14２. Recurrent Neural Networks 15３. Encoder-Decoder Model 16C. Proposed Encoders-Decoder Model 18IV. Results 20A. Reconstruction Experiment 20１. Experimental Setup 20２. Result 21B. Marker Classification (조사, 助詞, Josa, 토씨) 23１. Experimental Setup 23２. Result 24C. Spelling Correction 25１. Experimental Setup 25２. Result 26３. Candidate Scoring Experiment 30V. Conclusion 32References 33
최근 본 자료
댓글(0)
0