한국어 신어 탐색 방법론의 실제
On the Methodology for the Detection of Korean Neologisms
0
조회
0
다운로드
9
인용
0
참고문헌
키워드
초록
This study focuses on the methodology of neologism detection as an intermediate step in neologism extraction and analysis, rather than stressing the results of such extraction and analysis. As neologism research rarely discusses the issue of semi-automatic detection, this paper seeks to provide an overview of the status of the matter and discuss a number of issues related to the methodology of neologism extraction which can arise in the process of manual and automatic analyses so as to determine the significance of methodology in the analysis of neologisms. Section 2 presents the Neologism Investigation project carried out by the National Institute of the Korean Language, which consists of a systematic and comprehensive investigation of neologisms, and examines changes in methodology from a synchronic perspective. Section 3 reviews the general methodology of semi-automatic neologism detection, which was set out around 2010. Moreover, it discusses the actual process of manual analysis, including the analysis of data formats, and examines how the characteristics of both high-level and low-level automatic morpheme analyzers, which reflect the results of natural language processing research, impact the efficiency of neologism extraction so as to discuss the status of natural language processing methodology. Finally, Section 4 briefly discusses the limitations and significance of the neologism detection methodology.
Abstract
This study focuses on the methodology of neologism detection as an intermediate step in neologism extraction and analysis, rather than stressing the results of such extraction and analysis. As neologism research rarely discusses the issue of semi-automatic detection, this paper seeks to provide an overview of the status of the matter and discuss a number of issues related to the methodology of neologism extraction which can arise in the process of manual and automatic analyses so as to determine the significance of methodology in the analysis of neologisms. Section 2 presents the Neologism Investigation project carried out by the National Institute of the Korean Language, which consists of a systematic and comprehensive investigation of neologisms, and examines changes in methodology from a synchronic perspective. Section 3 reviews the general methodology of semi-automatic neologism detection, which was set out around 2010. Moreover, it discusses the actual process of manual analysis, including the analysis of data formats, and examines how the characteristics of both high-level and low-level automatic morpheme analyzers, which reflect the results of natural language processing research, impact the efficiency of neologism extraction so as to discuss the status of natural language processing methodology. Finally, Section 4 briefly discusses the limitations and significance of the neologism detection methodology.
참고문헌 (14)
- 김동의, "신어를 찾아내고 의미를 기술하여 관리하는 신어 조사용 프로그램의 설계 및 구현", 정보과학회논문지 : 소프트웨어 및 응용, 40(12), pp.882~894 (2013), 한국정보과학회
- 남길임, "신어의 빈도와 관련한 몇 가지 문제", 한국어 의미학, 68, pp.213~239 (2020), 한국어의미학회[DOI]
- 신준철, "한국어 품사 및 동형이의어 태깅을 위한 단계별 전이모델", 정보과학회논문지 : 소프트웨어 및 응용, 39(11), pp.889~901 (2012), 한국정보과학회
- 최혜원, "사회 변동에 따른 어휘 변화-국립국어원 신어 사업을 중심으로-", 2018 국제한국어교육학회 춘계학술발표논문집, pp.37~50 (2018), 국제한국어교육학회
- Boussidan, A., "Dynamics of semantic change: Detecting, analyzing and modeling semantic change in corpus in short diachrony", Doctor, pp.2013
- Breen, J., "Identification of neologisms in Japanese by corpus analysis", Proceedings of eLexicography in the 21st centry conference, pp.13~22 (2009)
- Cabré Castellví, M. T., "Towards a new approach to the study of neology", Neologica, 2012(6), pp.63~80 (2012)
- Falk, I., "From Non Word to New Word:Aunomatically Identifying Neologisms in French Newspapers", Proceedings of the International Conference on Language Resources and Evaluation (2014), LREC
- Garcia-Fernandez, A., "Méthodes pour l’archéologie linguistique: datation par combinaison d’indices temporels", Actes du septième DÉfi Fouille de Textes, pp.29~40 (2011)
- Issac, Fabrice, "Cybernéologisme : Quelques outils informatiques pour’identification et le traitement des néologismes sur le web", Langages, 183, pp.89~104 (2011)
- Kaji, N., "Splitting noun compounds via monolingual and bilingual paraphrasing: A study on japanese katakana words", Proceedings of the 2011 Conference on Empirical Methods in Natural Language Processing, pp.959~969 (2011)
- Kerremans, D., "Current methods in historical semantics", pp.59~96 (2012)
- Rundell, M., "A taste for corpora", pp.257~282 (2011)
- Sagi, E., "Current methods in historical semantics", pp.161~183 (2009)