한국어 학습자의 자동 L1 판별을 위한 언어 자질 연구
Examination of Language Features for Identification of KSL Learners’ L1
0
조회
0
다운로드
0
인용
0
참고문헌
키워드
초록
This study aims to clarify language features that can be used to discriminate the L1 of Korean learners. Native Language Identification, namely NLI, refers to the work of automatically checking the learners’ first language based on the target language produced by the learners who acquire the second language. In this study, intermediate learner data from three different L1 groups were used. These data were selected from the corpus of Korean learners of the National Institute of the Korean Language. The feature used in NLI was the n-gram frequency of individual Korean characters, combined characters, morphemes, parts of speech, and words in the corpus, as well as the tf-idf values of each feature. As for the method of NLI, the chi-square test and cosine similarity values were used. Although the corpus used in this study has some limitations, we succeeded in finding out some language qualities that can be tested.
Abstract
This study aims to clarify language features that can be used to discriminate the L1 of Korean learners. Native Language Identification, namely NLI, refers to the work of automatically checking the learners’ first language based on the target language produced by the learners who acquire the second language. In this study, intermediate learner data from three different L1 groups were used. These data were selected from the corpus of Korean learners of the National Institute of the Korean Language. The feature used in NLI was the n-gram frequency of individual Korean characters, combined characters, morphemes, parts of speech, and words in the corpus, as well as the tf-idf values of each feature. As for the method of NLI, the chi-square test and cosine similarity values were used. Although the corpus used in this study has some limitations, we succeeded in finding out some language qualities that can be tested.
참고문헌 (18)
- 강남준, "독립신문 논설의 형태 주석 말뭉치를 활용한 논설 저자 판별 연구 －어미 사용빈도 분석을 중심으로－", 한국사전학, (15), pp.73~101 (2010), 한국사전학회[DOI]
- 문한별, "소설 코퍼스를 활용한 ‘서동산’의 소설 『염마』의 저자 판별", 어문론집, 78, pp.63~91 (2019), 중앙어문학회[DOI]
- 최지명, "기계학습 알고리즘을 이용한 한국어 텍스트 저자 판별", 석사, pp.2015
- 한나래, "빈도 정보를 이용한 한국어 저자 판별", 인지과학, 20(2), pp.225~241 (2009), 한국인지과학회[DOI]
- Brooke, J., "Robust, lexicalized native language identification", Proceedings of COLING 2012, pp.391~408 (2012)
- Bykh, S., "Native Language Identification using Recurring n-grams - Investigating Abstraction and Domain Dependence-grams–Investigating Abstraction and Domain Dependence", Proceedings of COLING 2012, pp.425~440 (2012)
- Granger, S., "The Cambridge Handbook of Learner Corpus Research" (2015), Cambridge University Press
- Ionescu et al., "Can characters reveal your native language? A language-independent approach to native language identification", Proceedings of the 2014 Conference on Empirical Methods in Natural Language Processing (EMNLP), pp.1363~1373 (2014)
- Jarvis, S., "Maximizing classification accuracy in native language identification", Proceedings of the Eighth Workshop on Innovative Use of NLP for Building Educational Applications, pp.111~118 (2013)
- Jarvis, S., "The Cambridge Handbook of Learner Corpus Research", pp.606~627 (2015), Cambridge University Press
- Koppel, M., "Determining an author’s native language by mining a text for errors", Proceedings of the eleventh ACM SIGKDD international conference on Knowledge discovery in data mining, pp.624~628 (2005)
- Malmasi, "Large-scale native language identification with cross-corpus evaluation", Proceedings of the 2015 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, pp.1403~1409 (2015)
- Malmasi, "A report on the 2017 native language identification shared task", Proceedings of the 12th Workshop on Innovative Use of NLP for Building Educational Applications, pp.62~75 (2017)
- Tetreault, J., "Native tongues, lost and found: Resources and empirical evaluations in native language identification", Proceedings of COLING 2012, pp.2585~2602 (2012)
- Tomokiyo, L. M., "You’re not from’round here, are you? Naive Bayes detection of non-native utterances", Second Meeting of the North American Chapter of the Association for Computational Linguistics (2001)
- Tsur, O., "Using classifier features for studying the effect of native language on the choice of written second language words", Proceedings of the Workshop on Cognitive Aspects of Computational Language Acquisition, pp.9~16 (2007)
- Wong, S. M. J., "Contrastive analysis and native language identification", Proceedings of the Australasian Language Technology Association Workshop 2009, pp.53~61 (2009)
- Wong, S. M. J., "Exploiting parse structures for native language identification", Proceedings of the 2011 Conference on Empirical Methods in Natural Language Processing, pp.1600~1610 (2011)