청소년 언어문화 개선을 위한 교육 프로그램 연구 - ‘청소년 우리말 지킴이’ 사례를 중심으로

김철희 ( Kim Chulhui ),이혜경 ( Lee Hyekyung ) 한국공공언어학회 2019 공공언어학 Vol.1 No.0

This study is a study that suggests the case of education program of 'Youth Protector of Korea' which has been implemented and improved for 7 years after it was founded in Inha University, Korea. As a result of the study, 'The Korean Language Conservation Teacher' education program for improving the youth language culture was based on the theoretical model, peer subjectivity, sustainability and actuality, subject language education, and the instrumentality of knowledge. In addition, it was possible to organize mid - and long - term plans such as short - time within 2 months and club activities throughout the year. As a result of the education program, most of the students who are interested in the language and have middle level Korean ability completed the education program by completing the final research report. They were also taught profanity and profanity, correct use of Korean language, The evaluation has increased. This study is meaningful in terms of suggesting examples that can be used in the development of an effective educational program for improving the language culture of the youth that can overcome the limitations of existing education programs.

작문 수준에 따른 통사적 복잡성과 유창성 연구

김철희 ( Kim Chulhui ) 한국문법교육학회 2020 문법 교육 Vol.40 No.-

In Korean writing, the proposition that it is better to write short sentences needs to be studied academically. The purpose of this study is to statistically analyze the syntactic complexity and fluency characteristics of learner texts according to the writing level in terms of sentence length. The hypotheses of this study are as follows. First, syntactic complexity and fluency will differ depending on the level of writing. Second, syntactic complexity and fluency will have a correlation with the level of writing. Third, Syntax complexity and fluency are correlated. As a result of the study, first, syntax complexity and fluency were significantly different according to the writing level because the upper text was high and the lower text was low. Second, syntactic fluency was significantly correlated with the high upper text and lower text. Third, syntax complexity and fluency were not significantly correlated in the upper text group, but there was a close correlation in the lower text group.

디지털 기반 작문 교육을 위한 학습분석학의 역할과 과제 - 작문분석학을 중심으로 -

김철희 ( Kim Chulhui ) 한국작문학회 2021 작문연구 Vol.- No.49

이 연구의 목적은 디지털 기반 작문 교육을 위한 학습분석학의 역할이 무엇인가를 탐색하는 데 있다. 이를 위해 디지털 기반의 작문 교육에 시사점을 제공할 수 있는 학습분석학을 이론적으로 검토하고, 학습분석학과 작문 교육 논의가 융합적으로 전개되고 있는 영미권의 작문분석학 담론을 검토하였다. 그리고 이를 바탕으로 디지털 기반 작문 교육을 위한 학습분석학의 역할과 과제를 작문 교육 데이터, 작문 교육 환경, 디지털 쓰기 윤리 측면에서 논의 하였다. 연구 결과, 첫째, 작문 교육 데이터 측면에서 학습분석학은 작문 학습자의 프로파일 데이터, 작문 과정 데이터, 작문 결과 데이터 등을 종합적으로 수집·분석하여, 작문 학습자의 교수학습 및 작문 과정과 결과를 이해하고 예측하기 위한 이론적 기반을 제공할 수 있다. 둘째, 작문 교육 환경 측면에서 학습분석학은 디지털 리터러시 논의와 결합되어 디지털 기반 작문 교육 환경에서의 체제적 교수설계를 위한 이론적 기반을 제공할 수 있다. 이러한 작문교육이 실현되기 위해서는 학습자의 교육 데이터를 수집, 분석, 관리할 수 있는 작문 학습관리시스템의 개발의 필요성이 제기된다. 셋째, 디지털 쓰기 윤리 측면에서 학습분석학은 작문 교육 데이터 분석을 통하여 디지털 쓰기 윤리의 준수 여부를 판단할 수 있는 근거를 제공할 수 있다. 더불어 향후 정보 윤리 차원에서 작문 교육 데이터의 공개 여부나 수준, 보안 문제와 같은 논의의 필요성이 제기되므로 이에 대한 연구가 활발히 이루어져야 할 것이다. This study aims to explore the role of learning analytics for digital-based writing education. To this end, the discourse on learning and writing analysis in North America, which can provide implications for digital-based writing education, was reviewed. The results showed that, first, regarding writing education data, learning analytics can provide a theoretical basis for understanding and predicting the author’s writing process and results by comprehensively collecting and analyzing the profile data, writing process data, and writing result data of writing learners. Second, regarding the writing education environment, learning analytics can be combined with digital literacy discussion to provide a theoretical basis for systematic instructional design in the digital-based writing education environment. To achieve such writing education, a writing learning management system that can collect, analyze, and manage learners’ educational data must be developed. Third, regarding digital writing ethics, learning analytics can provide a basis for judging whether digital writing ethics are complied with through a data analysis of writing education. Additionally, discussion is needed from the perspective of future information ethics, such as whether to disclose writing education data, the appropriate level, and security issues.

사용자 사전과 형태소 토큰을 사용한 트랜스포머 기반 형태소 분석기

김동현(DongHyun Kim),김도국(Do-Guk Kim),김철희(ChulHui Kim),신명선(MyungSun Shin),서영덕(Young-Duk Seo) 한국스마트미디어학회 2023 스마트미디어저널 Vol.12 No.9

형태소는 한국어에서 의미를 가진 최소단위이기 때문에, 한국어 언어모델의 성능을 높이기 위해서는 정확한 형태소 분석기의 개발이 필요하다. 기존의 형태소 분석기는 대부분 어절 단위 토큰을 입력 값으로 학습하여 형태소 분석 결과를 제시한다. 하지만 한국어의 어절은 어근에 조사나 접사가 부착된 형태이기 때문에 어근이 같은 어절이어도 조사나 접사로 인해 의미가 달라지는 성향이 있다. 따라서 어절 단위 토큰을 사용하여 형태소를 학습하면 조사나 접사에 대한 오분류가 발생할 수 있다. 본 논문에서는 형태소 단위의 토큰을 사용하여 한국어 문장에 내재된 의미를 파악하고, Transformer를 사용한 시퀀스 생성 방식의 형태소 분석기를 제안한다. 또한, 미등록 단어 문제를 해결하기 위해 학습 말뭉치 데이터를 기반으로 사용자 사전을 구축하였다. 실험 과정에서 각 형태소 분석기가 출력한 형태소와 품사 태그를 함께 정답 데이터와 비교하여 성능을 측정하였으며, 실험 결과 본 논문에서 제시한 형태소 분석기가 기존 형태소 분석기에 비해 성능이 높음을 증명하였다. Since morphemes are the smallest unit of meaning in Korean, it is necessary to develop an accurate morphemes analyzer to improve the performance of the Korean language model. However, most existing analyzers present morpheme analysis results by learning word unit tokens as input values. However, since Korean words are consist of postpositions and affixes that are attached to the root, even if they have the same root, the meaning tends to change due to the postpositions or affixes. Therefore, learning morphemes using word unit tokens can lead to misclassification of postposition or affixes. In this paper, we use morpheme-level tokens to grasp the inherent meaning in Korean sentences and propose a morpheme analyzer based on a sequence generation method using Transformer. In addition, a user dictionary is constructed based on corpus data to solve the out-of-vocabulary problem. During the experiment, the morpheme and morpheme tags printed by each morpheme analyzer were compared with the correct answer data, and the experiment proved that the morpheme analyzer presented in this paper performed better than the existing morpheme analyzer.

저품격 언어의 분석적 고찰

박덕유(Deokyu Park),강미영(Miyeoung Kang),김수진(Sujin Kim),이혜경(Hyekyung Lee),이옥화(Okhwa Lee),김철희(Chulhui Kim) 한국중원언어학회 2014 언어학연구 Vol.0 No.30

This study aims to demand the improvement of a broadcasting language and raise the necessity for a nation-wide campaign for improving linguistic cultures with the correct and classy use of language, by investigating the actual usage of lower class language in media and showing the serious damage of the standard language. The categories of usage consist of vulgar expressions and terms against Eomun-gyubeom(Korean linguistic norm). Vulgar expressions mean poor quality in their contents and are divided into personality-insulting, discriminative, violent, and suggestive expressions, slang and chatting language, coarse language, unnecessary foreign language as well as loanwords. Terms against Eomun-gyubeom involve a nonstandard dialect, ungrammatical expressions, and errors in subtitles. Media language has a tremendous ripple effect on everyday language not just of the ordinary masses but also of the youth. Since media language is a public language targeted at unspecified masses, the lower class language that might damage our national language should be sublated in broadcasting.