http://chineseinput.net/에서 pinyin(병음)방식으로 중국어를 변환할 수 있습니다.
변환된 중국어를 복사하여 사용하시면 됩니다.
- 中文 을 입력하시려면 zhongwen을 입력하시고 space를누르시면됩니다.
- 北京 을 입력하시려면 beijing을 입력하시고 space를 누르시면 됩니다.
RISS 인기검색어
- 검색키워드
- 저자 : 추성엽 (검색결과 11 건)
- 무료
- 기관 내 무료
- 유료
-
-
Development of an AI Chatbot-Based Teaching Model for English Picture Book Retelling Activities
추성엽,민덕기 현대영어교육학회 2021 현대영어교육 Vol.22 No.4
The aim of this study was to develop and apply an AI chatbot-based teaching model for English picture book retelling activities in elementary schools. Participants were 18 students of the 5th grade who performed the retelling activity with three English picture books. AI chatbots were built with Google Dialogflow API. The criteria for building them were developed based on previous studies. Results are as follows. First, the model was composed of two lesson periods. In the first period, learners read the story together and checked their comprehension. In the next period, a teacher modelled retelling to students and the AI chatbots mediated learners’ retelling by asking questions. Finally, learners independently retold the story. Second, the criteria consisted of linguistic and affective perspectives, with four elements for each. Finally, students’ productions showed that the design of the chatbots’ prompts and scaffoldings partially affected students’ production. Moreover, the chatbots’ utterances should be sophisticatedly designed according to learners’ levels to gradually elicit their productions. This study suggests that integrating AI chatbots into classrooms can mediate young learners’ story retelling to partially support instructors who teach English reading skills in regular classes.
-
영어 상호작용 촉진을 위한 과업 기반 AI 챗봇 활용 및 학생 발화 분석
추성엽(Chu, Seong Yeub),민덕기(Min, Deok Gi) 한국초등영어교육학회 2019 초등영어교육 Vol.25 No.2
This study aimed to explore the possibility of using artificial intelligence(AI) Chatbot in English class to facilitate communication. Participants were 19 students in 6 th grade and performed 3 interactive tasks with Google Dialogflow API Chatbot. Tasks were exchanging small talk(task1), information gap activity(task2), and solving problems(task3), adopted from elementary English textbooks. The conversations were transcribed by the history function of Dialogflow and analyzed quantitatively to examine the production of participants and the success rates of each task and discourse. Furthermore, quantitative and qualitative analyses were executed to investigate how the prompts, activated by Chatbot, work as negotiation of meaning and elicitation to proceed interaction. The results revealed that the average t-unit of participants’ production showed 10, and they tended to speak 3-4 words in conversation. Next, the success rates of discourse and task were different for each task. The rate of task1 and task2 showed more than 65% compared to the task3. Despite the rate, Chatbot’s prompts provided meaningful effect on developing communicative ability by leading continual talk. Eventually, this study gave suggestion for integrating AI Chatbot into classroom to provide affordances for students’ using English, and for future progress of AI Chatbots as tools in foreign language education.
-
초등영어 과업 기반 AI 챗봇 개발 : 대화 관리 알고리즘을 활용한 탈 과업 방지를 중심으로
추성엽(Chu, Seong Yeub),이수민(Lee, Soo Min),민덕기(Min, Deok Gi) 한국초등영어교육학회 2021 초등영어교육 Vol.27 No.4
This study aimed to develop task-based AI chatbots for primary English that prevent task interruptions based on a dialogue management algorithm. The participants were 18 students from an elementary school located in Seoul. The results were as follows. Firstly, two strategies for dialogue management were determined by referring to previous research: negotiation of meaning and context management. Dialogflow API was used to build the AI chatbots applying the algorithm. Entity, Prompts, and Context, among the API’s various functions, were mainly used to implement the dialogue management algorithm. Secondly, the discourse transcript between the chatbots and learners was analyzed according to the two strategies. Above all, the negotiation of meaning strategy was implemented well to prevent the interruption of communication by providing different prompts, including corrective feedback. Next, the context management strategy was also activated properly to resolve dialogue breaks by providing scaffoldings and transforming topics. However, some recognition errors occurred during the communication due to the chatbots’ incomplete recognition rate of Korean young language learners’ spoken English. Hence, there need to be in-depth studies on the measures to make up for these problems. Nevertheless, the current study may encourage further research on developing AI chatbots for various tasks by preventing task interruptions.
-
자연어 툴킷 및 AI 챗봇을 활용한 초등영어 어휘평가 자동화 알고리즘 개발 연구
추성엽(Chu, Seong Yeub),민덕기(Min, Deok Gi) 한국초등영어교육학회 2020 초등영어교육 Vol.26 No.2
The purpose of this study aims to develop the algorithm that automatically assesses English vocabulary from students’ discourses by using the natural language toolkit (NLTK) and the artificial intelligence (AI) chatbot. The way to build the algorithm was as follows: First, three task-based AI chatbots were built by using Google Dialogflow API (Application Programming Interface) and discourses were transcribed automatically by the API’s history function. Second, the vocabulary data from three objective assessment criteria (Compleat Lexical Tutor VP-kids, CEFR, CEFR-J) were compared with textbooks, and new criteria were reorganized. Third, the discourses were tokenized and the parts of speech (POS) of the words utilized throughout the discourses were tagged by using Python programming language and the NLTK. Furthermore, different meanings of the vocabularies, depending on contexts, were analyzed and graded through Python text mining. Finally, the results were confirmed by experimentally distributing the utterance data from a 6th-grade student interaction with a chatbot among the three chatbots used in the study. Through the application of the algorithm, the vocabularies were evaluated properly by showing the expected results. However, the gradual development of the NLTK POS tagger is needed as some words were tagged incorrectly. Nevertheless, this algorithm showed the possibility of a collaboration of human, AI chatbots, and automation technology for highly efficient English assessment.
-
-
심규남,추성엽,권해경,이수민,민덕기 한국영어평가학회 2021 영어평가 Vol.16 No.2
The purpose of this study is to design a self-assessment model and put it into primary English class. This study also aims to investigate not only how teachers perceive the selfassessment they currently use but how students see new self-assessment using AI chatbots. To the research, a model of self-assessment using an AI chatbot was designed and implemented by considering the teaching schedule and the assessment context of the school. A survey was also conducted to gain what the teachers believed regarding the self-assessment, then a meta-cognition questionnaire including interview questions was constructed to obtain what the students did and what they perceived while assessing themselves. According to the results of the study, the self-assessments operated properly. The participant teachers neither use self-assessment as a major assessment method nor utilize it for school records as they believed that the result of the student self-assessment would be subjective and unreliable. However, the results of the study indicate that students are able to play a role as an assessor with an appropriately developed rating scale and careful guidance. The students also used their meta-cognitive strategies properly while doing the assessment. Some implications are presented in the last part of the study.
-
AI 챗봇 매개 초등영어 과정중심 평가 과업의 개발 및 적용
심규남,송은주,추성엽,권해경,민덕기 한국영어평가학회 2020 영어평가 Vol.15 No.1
The purpose of this study aims to develop AI mediated assessment tasks and put them into primary English teaching practice. Taking into account the teaching and assessment context of primary English teaching, and also the mainstream theories of process-oriented assessment, a model of AI chatbot mediated process-oriented assessment was developed. To conduct the research, five task types were selected; in line with this, AI chatbots were developed two times. After that, the chatbots were applied to primary English classes. According to the results of the study, the AI chatbots were operated properly after correcting operation errors that occurred at the first trial. The interaction between the chatbot and the students played a role as scaffolding, which could make the students progress in addressing the tasks; through this, especially some underachievers improved their English communication skills. However, there are still some issues that need to be addressed, such as designing AI chatbot tasks according to the English levels of the students as well as providing the teachers with in-service education programs regarding the chatbot platforms. Other issues needing further investigation were identified in the last part of the study.
-
변광식,김상부,김종근,추성엽 한국산업경영시스템학회 2008 한국산업경영시스템학회 학술대회 Vol.2008 No.추계
FMECA is one of the useful engineering tools for examining the potential failure modes within a system and its equipment and also for determining their effects on equipment and system performance. For CA (criticality analysis) procedure, β-value (the failure effect probability) should be estimated properly for an accurate identification of the critical items of system. In real applications, however, a subjective judgement of β-value is usually adopted. In this study, some guidances on the proper uses of β-value are considered. An alternative method for estimating β-value based on conditional probability is suggested and an illustrative example is given.
-
KCI연관 검색어 추천
이 검색어로 많이 본 자료
활용도 높은 자료
