Can Korean Language Models Detect Social Registers in Utterances?
0
조회
0
다운로드
0
인용
0
참고문헌
키워드
초록
This article investigates the capacity of the deep-learning algorithm to learn social register features from textual input, focusing on an interdisciplinary exploration at the intersection of sociolinguistics and computational linguistics. Languages encompass diverse aspects that are intricately linked to social contexts, implying that the ability to generate and comprehend linguistic expressions within specific social environments is an integral facet of communication competence. Such social factors influencing linguistic expressions, or social registers, encompass elements such as age, sex and gender, interlocutor relationship, and more. This study expands upon prior research on social registers by employing data-driven methods and deep learning skills to classify transcribed Korean language into predefined register classes based on features of sex, age, and kinship. Specifically, methodologies of transfer learning and in-context learning are utilized for classification tasks. However, both methods demonstrate poor performance in identifying the specified features, highlighting potential challenges in employing deep learning approaches for language use that is socially influenced.
Abstract
This article investigates the capacity of the deep-learning algorithm to learn social register features from textual input, focusing on an interdisciplinary exploration at the intersection of sociolinguistics and computational linguistics. Languages encompass diverse aspects that are intricately linked to social contexts, implying that the ability to generate and comprehend linguistic expressions within specific social environments is an integral facet of communication competence. Such social factors influencing linguistic expressions, or social registers, encompass elements such as age, sex and gender, interlocutor relationship, and more. This study expands upon prior research on social registers by employing data-driven methods and deep learning skills to classify transcribed Korean language into predefined register classes based on features of sex, age, and kinship. Specifically, methodologies of transfer learning and in-context learning are utilized for classification tasks. However, both methods demonstrate poor performance in identifying the specified features, highlighting potential challenges in employing deep learning approaches for language use that is socially influenced.
참고문헌 (22)
- Biber, Douglas, "Register, Genre, and Style" (2019), Cambridge University Press
- Cheshire, Jenny, "Style and Sociolinguistic Variation", Language, 83(2), pp.432~435 (2007)
- 조은, "Representation of Native English Teachers and Korean English Teachers in Korean English Newspapers: A Corpus-based Critical Discourse Analysis", 사회언어학, 31(2), pp.95~123 (2023), 한국사회언어학회
- 조용준, "한국어 의외성 표지 ‘-구나’, ‘-네’, ‘-다’의 사회언어적 변이 연구", 사회언어학, 24(1), pp.241~269 (2016), 한국사회언어학회[DOI]
- 최윤지, "텔레비전 뉴스의 합쇼체와 해요체 사용에 관련된 언어 외적 변인 고찰: 말뭉치의 계량적 분석을 바탕으로", 사회언어학, 26(4), pp.179~210 (2018), 한국사회언어학회[DOI]
- 정유진, "사용역에 따른 MAN과 WOMAN의 연어적 특성", 언어정보, (24), pp.51~76 (2017), 언어정보연구소
- 한희정, "언어 사용역에 따른 접속 부사의 사용 양상 연구", 한국어 의미학, 54, pp.175~202 (2016), 한국어의미학회[DOI]
- Hatim, Basil, "Discourse and the Translator" (1990), Longman
- Holmes, Janet, "An Introduction to Sociolinguistics" (1992), Longman
- 홍혜란, "한국어 교육을 위한 시제 사용 양상 연구- 사용역에 따른 분포와 담화 기능을 중심으로 -", 언어사실과 관점, 42, pp.159~186 (2017), 언어정보연구원[DOI]
- Hymes, Dell, "Foundations in Sociolinguistics: An Ethnographic Approach" (2001), Psychology Press
- 강혜림, "한국어 부사의 사용역 연구: 구어 담화에서 격식", 비격식 사용역을 중심으로, 2021, pp.(99), 1~21[DOI]
- Lee, Sangah, "KR-BERT: A Small-Scale Korean-Specific Language Model", arXiv. preprint arXiv:2008.03979, ~ (2020)
- 남길임, "사용역에 따른 비윤리적 표현의 분포와 사용 양상 연구 : ‘방송 대화’와 ‘메신저 대화’를 중심으로", 사회언어학, 30(3), pp.91~119 (2022), 한국사회언어학회[DOI]
- Nguyen, Dong, A., "Computational Sociolinguistics: A Survey", Computational Linguistics, 42(3), pp.537~593 (2016)
- 오지은, "드라마에서 재현된 성별 언어 사용에 대한 20대 초반의 언어 태도", 사회언어학, 30(1), pp.167~209 (2022), 한국사회언어학회[DOI]
- Park Sungjoon, "KLUE: Korean Language Understanding Evaluation", arXiv. preprint arXiv:2105.09680, ~ (2021)
- Paszke Adam, "Advances in Neural Information Processing Systems" (2019), Curran Associates, Inc
- Radford Alec, "Language Models Are Unsupervised Multitask Learners", OpenAI Blog, 1(8), pp.9~ (2019)
- Wang Alex, "GLUE: A Multi-Task Benchmark and Analysis Platform for Natural Language Understanding", arXiv. preprint arXiv:1804.07461, ~ (2018)
- Wolf Thomas, "Transformers : State-of-the-art Natural Language Processing", Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing: System Demonstrations, pp.38~45 (2020), Association for Computational Linguistics
- Xiao, Richard, "A Corpus-based Sociolinguistic Study of Amplifiers in British English", Sociolinguistic Studies, 1(2), pp.241~273 (2007)