Journal of information and communication convergence engineering

The Korea Institute of Information and Commucation Engineering (한국정보통신학회)
권호 표지
DOI QR코드

DOI QR Code

Design of an Automatic Summary System for Minutes Using Virtual Reality

  • Amsuk Oh (Department of Digital Contents, TongMyong University)
  • Received : 2023.06.21
  • Accepted : 2023.08.10
  • Published : 2023.09.30
Download PDF
⟨ Previous Next ⟩

Abstract

Owing to the environment in which it has become difficult to face people, on-tact communication has been activated, and online video conferencing platforms have become indispensable collaboration tools. Although costs have dropped and productivity has improved, communication remains poor. Recently, various companies, including existing online videoconferencing companies, have attempted to solve communication problems by establishing a videoconferencing platform within the virtual reality (Virtual Reality) space. Although the VR videoconference platform has only improved upon the benefits of existing video conferences, the problem of manually summarizing minutes because there is no function to summarize minute documents still remains. Therefore, this study proposes a method for establishing a meeting minute summary system without applying cases to a VR videoconference platform. This study aims to solve the problem of communication difficulties by combining VR, a metaverse technology, with an existing online video conferencing platform.

Keywords

References

  1. J. Edvardsson, H. W. Linderholm, B. Gunnarson, A. Hansson, T. T. Chen, and H. Gart ner, "To organize a conference under ever-changing conditions - Editorial to the special issue from the TRACE 2021 virtual meeting," Dendrochronologia, vol. 76, Dec. 2022. DOI: 10.1016/j.dendro.2022.126022.
  2. S. Bhargava, N. Negbenebor, R. Sadoughifar, S. Ahmad, and G. Kroumpouzos, "Virtual conferences and e-learning in dermatology during COVID-19 pandemic: Results of a web-based, global survey," Clinics in Dermatology, vol. 39, no. 3, pp. 461-466, May 2021. DOI: 10.1016/j.clindermatol.2021.06.002.
  3. A. Aghajanyan, A. Shrivastava, A. Gupta, and N. Goyal, "Better fine-tuning by reducing representational collapse," arXiv preprint arXiv:2008.03156v1, Aug. 2022. DOI: 10.48550/arXiv.2008.03156.
  4. J. Bradbury, S. Merity, C. Xiong, and R. Socher, "Quasi-recurrent neural networks," arXiv preprint arXiv:1611.01576v2, Nov. 2016. DOI: 10.48550/arXiv.1611.01576.
  5. H. Jiang, P. He, W. Chen, X. Liu, J. Gao, and T. Zhao, "SMART: Robust and efficient fine-tuning for pre-trained natural language models through principled regularized optimization," in The 58th annual meeting of the Association for Computational Linguistics (ACL 2020), arXiv preprint arXiv:1911.03437v5, pp. 2177-2190, Nov. 2019. DOI: 10.48550/arXiv.1911.03437.
  6. J. Devlin, M-W. Chang, K. Lee, and K. Toutanova, "BERT: Pretraining of deep bidirectional transformers for language understanding," in Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, arXiv preprint arXiv:1810.04805v2, vol. 1, pp. 4171-4186, Oct. 2018. DOI: 10.48550/arXiv.1810.04805.
  7. D. P. Kingma and M. Welling, "Auto-encoding variational bayes," arXiv preprint arXiv:1312.6114v11, Dec. 2013. DOI: 10.48550/arXiv.1312.6114.
  8. Z. Yang, Z. Dai, Y. Yang, J. Carbonell, R. Salakhutdinov, and Q. V. Le, "XLNet: Generalized autoregressive pretraining for language understanding", Neural Information Processing Systems 32 (NeurIPS 2019), arXiv preprint arXiv:1906.08237v2, pp. 57530-5763, Jul. 2019. DOI: 10.48550/arXiv.1906.08237.
  9. Y. Liu, M. Ott, N. Goyal, J. Du, M. Joshi, D. Chen, O. Levy, M. Lewis, L. Zettlemoyer, and V. Stoyanov, "RoBERTa: A robustly optimized bert pretraining approach," arXiv preprint arXiv: 1907.11692, Jul. 2019. DOI: 10.48550/arXiv.1907.11692.
  10. C. Raffel, N. Shazeer, A. Roberts, K. Lee, S. Narang, M. Matena, Y. Zhou, W. Li, and P. J. Liu, "Exploring the limits of transfer learning with a unified text-to-text transformer," The Journal of Machine Learning Research, arXiv preprint arXiv:1910.10683v3, vol. 21, no. 1, pp. 1-67, Jan. 2020. DOI: 10.48550/arXiv.1910.10683.