영어자원문법을 활용한 신경망 기계번역의 데이터 증강과 성능 평가
DC Field | Value | Language |
---|---|---|
dc.contributor.author | 왕규현 | - |
dc.contributor.author | 송상헌 | - |
dc.date.accessioned | 2022-03-13T06:40:23Z | - |
dc.date.available | 2022-03-13T06:40:23Z | - |
dc.date.created | 2021-12-06 | - |
dc.date.issued | 2021 | - |
dc.identifier.issn | 1598-1886 | - |
dc.identifier.uri | https://scholar.korea.ac.kr/handle/2021.sw.korea/138814 | - |
dc.description.abstract | Wang, Guehyun; Song, Sanghoun (2021), “Evaluation of Neural Machine Translation Trained by Augmented Data Using English Resource Grammar,” Language and Information Society 42. 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. | - |
dc.language | Korean | - |
dc.language.iso | ko | - |
dc.publisher | 서강대학교 언어정보연구소 | - |
dc.title | 영어자원문법을 활용한 신경망 기계번역의 데이터 증강과 성능 평가 | - |
dc.title.alternative | Evaluation of Neural Machine Translation Trained by Augmented Data Using English Resource Grammar | - |
dc.type | Article | - |
dc.contributor.affiliatedAuthor | 송상헌 | - |
dc.identifier.doi | 10.29211/soli.2021.42..007 | - |
dc.identifier.bibliographicCitation | 언어와 정보 사회, v.42, pp.179 - 200 | - |
dc.relation.isPartOf | 언어와 정보 사회 | - |
dc.citation.title | 언어와 정보 사회 | - |
dc.citation.volume | 42 | - |
dc.citation.startPage | 179 | - |
dc.citation.endPage | 200 | - |
dc.type.rims | ART | - |
dc.identifier.kciid | ART002704138 | - |
dc.description.journalClass | 2 | - |
dc.description.journalRegisteredClass | kci | - |
dc.subject.keywordAuthor | ERG | - |
dc.subject.keywordAuthor | data augmentation | - |
dc.subject.keywordAuthor | deep learning | - |
dc.subject.keywordAuthor | evaluation metric | - |
dc.subject.keywordAuthor | machine translation | - |
dc.subject.keywordAuthor | parallel corpus | - |
dc.subject.keywordAuthor | paraphrasing | - |
dc.subject.keywordAuthor | 기계번역 | - |
dc.subject.keywordAuthor | 다시쓰기 | - |
dc.subject.keywordAuthor | 데이터 증강 | - |
dc.subject.keywordAuthor | 딥러닝 | - |
dc.subject.keywordAuthor | 병렬 코퍼스 | - |
dc.subject.keywordAuthor | 영어자원문법 | - |
dc.subject.keywordAuthor | 평가 방법 | - |
Items in ScholarWorks are protected by copyright, with all rights reserved, unless otherwise indicated.
(02841) 서울특별시 성북구 안암로 14502-3290-1114
COPYRIGHT © 2021 Korea University. All Rights Reserved.
Certain data included herein are derived from the © Web of Science of Clarivate Analytics. All rights reserved.
You may not copy or re-distribute this material in whole or in part without the prior written consent of Clarivate Analytics.