영어교육에서 AI 활용의 한계는 어디쯤일까?: 자동 지문 생성 및 자동 문항 생성의 활용 가능성 = What is the limit for using AI in English education?: Feasibility of using Automated Text Generation and Automated Item Generation.

다국어 초록 (Multilingual Abstract)

This study explores the feasibility of using Automated Text Generation (ATG) and Automated Item Generation (AIG) in the field of English education. To this end, 60 pre-service teachers directly tried the two programs and participated in improving the quality of the test item through post-editing. The results suggest the following: First, among the participants who corrected the test items of the participants in this experiment, the pre-service teachers modified their test item 391 times in total. Text correction accounted for 75.19% of the modifications, and option correction accounted for 24.8%. In the program user satisfaction survey, 86% of the ATG program respondents showed a positive attitude. In addition, the fact that none of the respondents selected 'very dissatisfied' suggests that there was a high possibility of using ATG at school. On the other hand, the AIG program respondents demonstrated a relatively low level of satisfaction. Overall, 43% responded positively but 33% of the total respondents took a negative stance. Improvements for both programs collected through open-ended questions were also presented. It is, however, important to note that evaluation of whether or not a post-editing attempt was appropriate was beyond the scope of this study.

참고문헌 (Reference)

1 김재상, "인간과 인공지능 기기의 상호작용이 EFL 환경에서 초등학생들의 협업적 언어습득에 미치는 영향" 광주교육대학교 2017

2 이용상 ; 신동광, "원격교육 시대의 인공지능 활용 온라인 평가" 학습자중심교과교육학회 20 (20): 389-407, 2020

3 신동광, "영어 읽기평가 문항의 지문 어휘통제 과정에서 나타난 한국 예비교사들의 재기술(paraphrase) 양상 분석" 한국멀티미디어언어교육학회 23 (23): 157-179, 2020

4 권서경 ; 신동광, "대학수학능력시험 영어영역 읽기 문항 난이도 요인 탐색: EBS 연계정책 변화를 중심으로" 한국영어교과교육학회 21 (21): 49-71, 2022

5 신동광 ; 전유아, "기계번역의 오류 양상과 사후수정(post-editing)이L2 쓰기 적절성에 미치는 영향" 한국영어교과교육학회 21 (21): 121-140, 2022

6 Meehan, J. R., "TALE-SPIN: An interactive program that writes stories" Morgan Kaufmann Inc 91-98, 1977

7 Ghumra, F., "OpenAI GPT-3, the most powerful language model:An overview"

8 Al-Yahya, M., "Ontology-based multiple choice question generation" 2014 : 274949-, 2014

9 Bormuth, J., "On a theory of achievement test items" University of Chicago Press 1969

10 Turner, S. R., "Minstrel: A computer model of creativity and storytelling" University of California 1993

11 Wachob, P., "Methods and materials for motivation and learner autonomy" 5 (5): 93-122, 2006

12 Brown, T. B., "Language models are few-shot learners. arXiv preprint"

13 Bejar, I., "Item generation for test development" Erlbaum 199-217, 2002

14 Heilman, M., "Good question! Statistical ranking for question generation" Association for Computational Linguistics 609-617, 2010

15 Liu, M., "G-Asks : An intelligent automatic question generation system for academic writing support" 3 (3): 101-124, 2012

16 Drasgow, F., "Educational measurement" American Council on Education 471-516, 2006

17 Lebowitz, M., "Creating a story-telling universe" Morgan Kaufmann Inc 63-65, 1983

18 Yacoubian, P., "CopyAI [Computer Software]" CopyAI Inc

19 Millman, J., "Computer-assisted writing of achievement test items : toward a future technology" 26 (26): 177-190, 1989

20 Klein, S., "Automatic novel writing:A status report" University of Wisconsin, Computer Science Department 1973

21 Gierl, M. J., "Automatic item generation, theory and practice" Routledge Chapman & Hall 2012

22 von Davier, M., "Automated item generation with Recurrent Neural Networks" 83 (83): 847-857, 2018

23 Lee, H., "AI Test Maker (ATM) [Computer Software]" LXPER Inc

24 Zeng, V., "A survey on Machine Reading Comprehension : Tasks, evaluation metrics and benchmark datasets" 10 : 7640-, 2020

25 Vinu, E. V., "A novel approach to generate MCQs from domain ontology : Considering DL semantics and open-world assumption" 34 : 40-54, 2015

26 Ras, E., "A hybrid engineering process for semi-automatic item generation" 2017