• 한국컴퓨터정보학회논문지
• /
• 제29권2호
• /
• pp.43-50
• /
• 2024

본 논문은 GPT-3.5 및 GPT-4와 같은 대규모 언어 모델의 한국어 감성 분석 성능을 ChatGPT API를 활용한 zero-shot 방법으로 평가하고, 이를 KoBERT와 같은 사전 학습된 한국어 모델들과 비교한다. 실험을 통해 영화, 게임, 쇼핑 등 다양한 분야의 한국어 감성 분석 데이터셋을 사용하여 모델들의 효율성을 검증한다. 실험 결과, LMKor-ELECTRA 모델이 F1-score 기준으로 가장 높은 성능을 보여주었으며, GPT-4는 특히 영화 및 쇼핑 데이터셋에서 높은 정확도와 F1-score를 기록하였다. 이는 zero-shot 학습 방식의 대규모 언어 모델이 특정 데이터셋에 대한 사전 학습 없이도 한국어 감성 분석에서 높은 성능을 발휘할 수 있음을 시사한다. 그러나 일부 데이터셋에서의 상대적으로 낮은 성능은 zero-shot 기반 방법론의 한계점으로 지적될 수 있다. 본 연구는 대규모 언어 모델의 한국어 감성 분석 활용 가능성을 탐구하며, 이 분야의 향후 연구 방향에 중요한 시사점을 제공한다.

• 한국어교육
• /
• 제29권3호
• /
• pp.227-253
• /
• 2018

The purpose of this study is to propose a plan for future developments of the Korean language textbooks for overseas by conducting the Importance-Performance Analysis (IPA) of the Korean language textbooks for overseas. For this purpose, this study analyse and evaluate the Korean language textbooks for overseas and the researches for developing Korean language textbooks for overseas. In this study, we have the IPA of the Korean language textbooks from the total of 158 surveys that were collected from teachers who teach Korean at King Sejong Institute and overseas university. The survey conducted about the Korean textbooks regarding the following questionnaires: 1) integrated and separated textbooks, 2) textbooks by learners' variables, 3) teaching materials by media type, 4) supplementary teaching materials, 5) diffusion and support of textbooks. The result of this survey found that supporting for the separated textbooks is needed, and there is a high demand for localized textbooks considering local characteristics. Furthermore, it is noteworthy that King Sejong Institute has a high demand for textbooks that can be downloaded from the web despite most of institutes are highly satisfied with paper textbooks. For the supplementary textbooks, it was found that vocabulary learning materials were needed for the King Sejong school students and additional reading materials for overseas college learners needed to be developed. We also found that it is necessary to support not only the development of textbooks but also smooth and efficient diffusion.

• Journal of information and communication convergence engineering
• /
• 제18권1호
• /
• pp.33-38
• /
• 2020

Elasticsearch is an open source search and analytics engine that can search petabytes of data in near real time. It is designed as a distributed system horizontally scalable and highly available. It provides RESTful APIs, thereby making it programming-language agnostic. Full text search of multilingual text requires language-specific analyzers and field mappings appropriate for indexing and searching multilingual text. Additionally, a language detector can be used in conjunction with the analyzers to improve the multilingual text search. Elasticsearch provides more than 40 language analysis plugins that can process text and extract language-specific tokens and language detector plugins that can determine the language of the given text. This study investigates three different approaches to index and search Chinese, Japanese, and Korean (CJK) text (single analyzer, multi-fields, and language detector-based), and identifies the advantages of the language detector-based approach compared to the other two.

• 한국언어정보학회:학술대회논문집
• /
• 한국언어정보학회 2005년도 하계 학술대회
• /
• pp.87-102
• /
• 2005

• 제어로봇시스템학회:학술대회논문집
• /
• 제어로봇시스템학회 1987년도 한국자동제어학술회의논문집; 한국과학기술대학, 충남; 16-17 Oct. 1987
• /
• pp.300-306
• /
• 1987

This paper deals with a modeling of manufacturing system and a model analysis by a SIMAN language. A flow of production process is analyzed, and a mathematical model on the basis of the analyzed data is simulated by a SIMAN language. An object of this study is to achieve an optimization of production a reduction of cost, and an improvement of quality by a applicable line-balancing technique and an optimization technique in a real factor induced an analysis and synthesis of the result of simulation.

• 영어어문교육
• /
• 제15권4호
• /
• pp.265-290
• /
• 2009

The present data-driven study attempted to explicate nonnative English teacher trainees' foreign language teaching anxiety in microteaching settings from their perspectives. It is assumed that nonnative English teachers or teacher trainees may experience anxiety not only as foreign language learners but also as foreign language teachers. In order to inquire into their anxiety, the researcher had 172 teacher trainees perform extended microteaching tasks and reflect on their teaching and anxiety through group discussion. Based on the analysis of their discussion, three aspects related to nonnative English teacher trainees' anxiety were identified. First, teacher trainees identified three main types of anxiety-provoking situations: communicative-competence-threatening situations, unexpected situations, and instruction-hindering situations. Second, they identified three sources of anxiety: limited ability to use English, lack of English teaching skills, and fear of criticism. Third, they were aware that they used diverse strategies to lower anxiety before and while teaching for different purposes. From their identification and awareness of anxiety-provoking situations, sources of anxiety, and anxiety-lowering strategies, they could reflect on professional qualifications as a foreign language teacher.

• 한국어교육
• /
• 제28권4호
• /
• pp.87-119
• /
• 2017

The purpose of this study is to classify research methods used in Korean language education studies with a focus on identifying how and what quantitative research methods are utilized in these studies. Analyzing articles published in the Journal of Korean Language Education from 2005 to 2016, we found a trend that as a replacement for secondary research, primary research played a more prominent role after 2010, as the number of quantitative studies and studies using mixed methods increased. We also found that within quantitative studies of Korean language education, research themes and statistical analyses became diversified after 2010. In order for quantitative research to contribute continuously to Korean language education, the quality of research has to improve. In particular, quantitative researchers in this area should: (a) increase their general understanding of statistical methods, (b) conduct "power analysis" to determine the appropriate sample size for hypothesis testing, and (c) be aware of measurement issues such as measurement equivalence and DIF when measuring latent psychological constructs. It is also important to notice that these points above should be considered carefully in the planning and designing stage for researchers.

• 한국어교육
• /
• 제23권1호
• /
• pp.77-100
• /
• 2012

This study investigates issues in relation to text segmenting, in particular, line breaks in Korean language textbooks. Research on L1 and L2 reading has shown that readers process texts by chunking (grouping words into phrases or meaningful syntactic units) and, therefore, phrase-cued texts are helpful for readers whose syntactic knowledge has not yet been fully developed. In other words, it would be important for language textbooks to avoid awkward syntactic divisions at the end of a line, in particular, those textbooks for beginners and intermediate level learners. According to our analysis of a number of major Korean language textbooks for beginner-level learners, however, many textbooks were found to display line-breaks of awkward syntactic division. Moreover, some textbooks displayed frequent instances where a single word (or eojeol in the case of Korean) is split between different lines. This can hamper not only learners' learning of the rules of spaces between eojeols in Korean, but also learners' development in automatic word recognition, which is an essential part of reading processes. Based on the findings of our textbook analysis and of existing research on reading, this study suggests ways to overcome awkward line-breaks in Korean language textbooks.

• 한국어교육
• /
• 제23권1호
• /
• pp.283-306
• /
• 2012

This study dealt with an issue of teaching Korean as a foreign language in North Korea through textbook analysis. The literature in this field has been quite rare compared to that in other fields in Korean language education, which is due to the adverse circumstances under which research into North Korea is currently carried out. The textbooks analyzed were 조선말회화(1) and 조선말회화(3) and the two learners who had studied Korean with these textbooks were interviewed. The main results show that (a) the grammar points in each chapter are unevenly distributed in 조선말회화(1), which makes it not look learner-centered; (b) each chapter in 조선말회화(1) is composed of speech acts, topics and situations, which renders it useful to its learners; (c) 조선말회화(3) emphasizes Korean oral discoursal features as a conversational textbook; and (d) 조선말회화(3) also covers much of reading comprehension-focused contents, which its learners may find burdensome. Foreseeing a possibility of teaching Korean as a foreign language in a reunified Korea makes it critical to carry out research into teaching Korean as a foreign language in North Korea. This calls for future collaborative research into this issue between two Koreas.

• 인지과학
• /
• 제10권2호
• /
• pp.35-43
• /
• 1999

본 논문에서는 현대 한국어에서 나타나는 언어 변화 현상에 대한 설명과 그러한 언어 현상이 언어 처리 시스템에 미칠 수 있는 영향을 연구한다. 현대 한국어에서는〔관형형 어미 + 의존 명사 + (조사)〕와 같은 통사론적 구성이 형태론적 구성으로 변화되는 과정이 나타나고 있으며 몇몇 형태에서는 문자 언어 생활에서도 두드러지게 나타나고 있다. 이러한 예로 통사론적 구성〔관형형 어미 + 의존명사‘데’(+조사)〕이‘-는데’로,〔관형형 어미 + 의존명사‘것’+ 조사〕구성이‘-는게’로 나타나고 있으며, 음성 언어 생활에서는 더욱 두드러지고 있어서 다른 어미와 구별하기 어렵다. 이와 같은 유형의 형태는 다른 접속 문 어미나 내포문 어미처럼 복합문 구성에 관여하는 것으로 파악할 수 있는데, 다른 어미와는 달리 이 형태 자체에 문법적인 격 기능이 융합되어 있다. 따라서, 이러한 형태에 대한 분석 방법은 언어 처리 시스템의 구성에 영향을 미칠 수 있으며, 자동 태깅 시스템. 통사 분석 시스템 등에는 특히 그러하다. 그러므로, 언어 처리 시스템의 설계에 이러한 언어 변화 현상이 반영될 필요가 있다.