한국융합학회논문지 (Journal of the Korea Convergence Society)

  • 제13권3호
  • /
  • Pages.11-22
  • /
  • 2022
  • /
  • 2233-4890(pISSN)
  • /
  • 2713-6353(eISSN)
한국융합학회 (Korea Convergence Society)
권호 표지
DOI QR코드

DOI QR Code

최신 대화형 에이전트 기반 상용화 교육 플랫폼 오류 분석

Error Analysis of Recent Conversational Agent-based Commercialization Education Platform

  • 이승준 (고려대학교 컴퓨터학과) ;
  • 박찬준 (고려대학교 컴퓨터학과) ;
  • 서재형 (고려대학교 컴퓨터학과) ;
  • 임희석 (고려대학교 컴퓨터학과)
  • Lee, Seungjun (Department of Computer Science and Engineering, Korea University) ;
  • Park, Chanjun (Department of Computer Science and Engineering, Korea University) ;
  • Seo, Jaehyung (Department of Computer Science and Engineering, Korea University) ;
  • Lim, Heuiseok (Department of Computer Science and Engineering, Korea University)
  • 투고 : 2021.12.03
  • 심사 : 2022.03.20
  • 발행 : 2022.03.28
PDF 다운로드
⟨ 이전 논문 다음 논문 ⟩

초록

최근 교육 분야에서 다양한 인공지능 기술을 활용한 연구와 개발이 이뤄지고 있다. 인공지능을 활용한 교육 중 특히 대화형 에이전트는 시간과 공간의 제약을 받지 않고 음성인식, 번역과 같은 다양한 인공지능 기술과 결합해 더 효과적인 언어 학습을 가능하게 한다. 본 논문은 상용화된 교육용 플랫폼 중 이용자 수가 많고 영어 학습을 위한 대화형 에이전트가 활용된 플랫폼에 대한 동향 분석을 진행하였다. 동향 분석을 통해 현재 상용화된 교육용 플랫폼의 대화형 에이전트는 여러 한계점과 문제점이 존재했다. 구체적인 문제점과 한계점 분석을 위해 사전 학습된 최신 대용량 대화 모델과 비교 실험을 진행하였고, 실험 방법으로 대화형 에이전트의 대답이 사람과 비슷한지를 평가하는 Sensibleness and Specificity Average (SSA) 휴먼 평가를 진행하였다. 실험 내용을 바탕으로, 효과적인 학습을 위해 개선방안으로 대용량 파라미터로 학습된 대화 모델, 교육 데이터, 정보 검색 기능의 필요성을 제안했다.

Recently, research and development using various Artificial Intelligence (AI) technologies are being conducted in the field of education. Among the AI in Education (AIEd), conversational agents are not limited by time and space, and can learn more effectively by combining them with various AI technologies such as voice recognition and translation. This paper conducted a trend analysis on platforms that have a large number of users and used conversational agents for English learning among commercialized application. Currently commercialized educational platforms using conversational agent through trend analysis has several limitations and problems. To analyze specific problems and limitations, a comparative experiment was conducted with the latest pre-trained large-capacity dialogue model. Sensibleness and Specificity Average (SSA) human evaluation was conducted to evaluate conversational human-likeness. Based on the experiment, this paper propose the need for trained with large-capacity parameters dialogue models, educational data, and information retrieval functions for effective English conversation learning.

키워드

과제정보

This research was supported by the MSIT(Ministry of Science and ICT), Korea, under the ITRC(Information Technology Research Center) support program(IITP-2018-0-01405) supervised by the IITP(Institute for Information & Communications Technology Planning & Evaluation) and supported by Basic Science Research Program through the National Research Foundation of Korea(NRF) funded by the Ministry of Education(NRF-2021R1A6A1A03045425).

참고문헌

  1. Z. Ruttkay & C. Pelachaud. (Eds.). (2006). From brows to trust: Evaluating embodied conversational agents, 7, Springer Science & Business Media.
  2. M. Lim. (2020). A Study on the Direction of Technology Education in the Age of Artificial Intelligence. Journal of Korean Practical Arts Education, 33(4), 81-102. https://doi.org/10.24062/kpae.2020.33.4.81
  3. L. Fryer & R. Carpenter. (2006). Bots as language learning tools. Language Learning & Technology, 10(3), 8-14.
  4. N. Y. Kim, Y. Cha & H. S. Kim. (2019). Future Eng lish learning: Chatbots and artificial intelligence. Multimedia-Assisted Language Learning, 22(3), 32-53. https://doi.org/10.15702/MALL.2019.22.3.32
  5. J. Li & D. Jurafsky. (2016). Neural net models for open-domain discourse coherence. arXiv preprint arXiv:1606.01545.
  6. B. Chantarotwong. (2006). The learning chatbot. Final year project.[Online]: http://courses.ischool.berkeley.edu/i256/f06/projects/bonniejc.pdf.
  7. D. Lee. (2018). A study for the development of an English learning chatbot system based on Artificial Intelligence. Secondary English Education, 11(1), 45-68. https://doi.org/10.20487/kasee.11.1.201802.45
  8. S. Zhang. et al. (2018). Personalizing dialogue agents: I have a dog, do you have pets too?. arXiv preprint arXiv:1801.07243.
  9. S. Roller. et al. (2020). Recipes for building an open-domain chatbot. arXiv preprint arXiv:2004.13637.
  10. J. Jia & M. Ruan. (2008, June). Use chatbot csiec to facilitate the individual learning in english instruction: A case study. In International conference on intelligent tutoring systems (pp. 706-708). Springer, Berlin, Heidelberg.
  11. J. In & J. Han. (2016). The prosodic changes of Korean English learners in robot assisted learning. Journal of The Korean Association of Information Education, 20(4), 323-332. https://doi.org/10.14352/jkaie.2016.20.4.323
  12. N. Y. Kim. (2019). A study on the use of artificial intelligence chatbots for improving English grammar skills. Journal of Digital Convergence, 17(8), 37-46. https://doi.org/10.14400/JDC.2019.17.8.037
  13. Y. Kim. (2020). Analysis of chatbots and chatbot builders for English language learning. Multimedia-Assisted Language Learning, 23(4), 161-182. https://doi.org/10.15702/MALL.2020.23.4.161
  14. J. E. Hyun & H. J. Im. (2019). Analysis and Implications of AI Speakers as English Learning Tools. The Journal of Mirae English Language and Literature 24(1), 201-219. https://doi.org/10.46449/MJELL.2019.02.24.1.201
  15. H. Kim & D. Shin. (2019). A study of AI chatbot as an assistant tool for school English curriculum. The Journal of Learner-Centered Curriculum and Instruction, 19(1), 89-110. DOI ; 10.22251/jlcci.2019.19.1.89
  16. K. Teske. (2017). Duolingo. Calico Journal, 34(3), 393-402. https://doi.org/10.1558/cj.32509
  17. J. Jang & S. Ye. (2021). Towards Continual Knowledge Learning of Language Models. arXiv preprint arXiv:2110.03215.
  18. M. Komeili, K. Shuster & J. Weston. (2021). Internet-augmented dialogue generation. arXiv preprint arXiv:2107.07566.
  19. J. Xu, A. Szlam & J. Weston. (2021). Beyond goldfish memory: Long-term open-domain conversation. arXiv preprint arXiv:2107.07567.
  20. L. Floridi & M. Chiriatti. (2020). GPT-3: Its nature, scope, limits, and consequences. Minds and Machines, 30(4), 681-694. https://doi.org/10.1007/s11023-020-09548-1
  21. T. Yoon & S. Lee. (2021). Effects of Primary ELLs' Affective Factors and Satisfaction through AI-based Speaking Activity. The Journal of the Korea Contents Association, 21(9), 34-41. DOI : 10.5392/JKCA.2021.21.09.034
  22. J. Sedoc. et al. (2019, June). ChatEval: A tool for chatbot evaluation. In Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics (Demonstrations) (pp. 60-65).
  23. S. Roller. et al. (2020). Recipes for building an open-domain chatbot. arXiv preprint arXiv:2004.13637.