DC Field | Value | Language |
---|---|---|
dc.contributor.advisor | 주재걸 | - |
dc.contributor.author | Kim, Do Hee | - |
dc.contributor.author | 김도희 | - |
dc.date.accessioned | 2024-07-26T19:31:15Z | - |
dc.date.available | 2024-07-26T19:31:15Z | - |
dc.date.issued | 2023 | - |
dc.identifier.uri | http://library.kaist.ac.kr/search/detail/view.do?bibCtrlNo=1051071&flag=dissertation | en_US |
dc.identifier.uri | http://hdl.handle.net/10203/321051 | - |
dc.description | 학위논문(석사) - 한국과학기술원 : 김재철AI대학원, 2023.8,[iii, 15 p. :] | - |
dc.description.abstract | Formality is one of the most important linguistic properties to determine the naturalness of translation. Although a target-side context contains formality-related tokens, the sparsity within the context makes it difficult for context-aware neural machine translation (NMT) models to properly discern them. In this paper, we introduce a novel training method to explicitly inform the NMT model by pinpointing key informative tokens using a formality classifier. Given a target context, the formality classifier guides the model to concentrate on the formality-related tokens within the context. Additionally, we modify the standard cross-entropy loss, especially toward the formality-related tokens obtained from the classifier. Experimental results show that our approaches not only improve overall translation quality but also reflect the appropriate formality from the target context. | - |
dc.language | eng | - |
dc.publisher | 한국과학기술원 | - |
dc.subject | 신경망 기계 번역▼a문맥 인식 번역▼a문체 생성 제어▼a단일 인코더 방법론 | - |
dc.subject | Neural machine translation▼aContext-aware translation▼aFormality control▼aSingle encoder approach | - |
dc.title | Towards formality-aware neural machine translation by leveraging context information | - |
dc.title.alternative | 문맥 정보를 활용한 문체 인식 신경망 기계 번역 | - |
dc.type | Thesis(Master) | - |
dc.identifier.CNRN | 325007 | - |
dc.description.department | 한국과학기술원 :김재철AI대학원, | - |
dc.contributor.alternativeauthor | Choo, Jaegul | - |
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.