Electronics and Telecommunications Trends (전자통신동향분석)

Electronics and Telecommunications Research Institute (한국전자통신연구원)
권호 표지
DOI QR코드

DOI QR Code

Trends and Future of Digital Personal Assistant

디지털 개인비서 동향과 미래

  • Published : 2021.02.01
Download PDF
⟨ Previous Next ⟩

Abstract

In this study, we introduce trends in and the future of digital personal assistants. Recently, digital personal assistants have begun to handle many tasks like humans by communicating with users in human language on smart devices such as smart phones, smart speakers, and smart cars. Their capabilities range from simple voice commands and chitchat to complex tasks such as device control, reservation, ordering, and scheduling. The digital personal assistants of the future will certainly speak like a person, have a person-like personality, see, hear, and analyze situations like a person, and become more human. Dialogue processing technology that makes them more human-like has developed into an end-to-end learning model based on deep neural networks in recent years. In addition, language models pre-trained from a large corpus make dialogue processing more natural and better understood. Advances in artificial intelligence such as dialogue processing technology will enable digital personal assistants to serve with more familiar and better performance in various areas.

Keywords

References

  1. S. Chourasia, "What are 10 best AI assistants of 2021?," Aug. 2020, https://techresearchonline.com/blog/best-ai-assistant-of-2021/#
  2. Pat Research, "Top 22 intelligent personal assistants or automated personal assistants,",https://www.predictiveanalyticstoday.com/top-intelligent-personal-assistants-automated-personal-assistants/#whatareintelligentpersonalassistantsorautomatedpersonalassistants
  3. LG CNS, "앱의 시대에서 가상 비서의 시대로, Virtual personal assistant," 2016, https://blog.lgcns.com/1241
  4. 임영신, "폰안의 비서, 그들만의 전쟁을 시작했다," 매일경제, 2020.11.1.
  5. 삼성 빅스비, https://www.samsung.com/sec/apps/bixby/
  6. NUGU, https://www.nugu.co.kr/
  7. KT 기가지니, https://gigagenie.kt.com/main.do
  8. 김주완, "책 펴기만 하면 대신 읽어주네 일상 깊숙히 파고드는 AI," 한국경제, 2020.11.9.
  9. 카카오 미니헥사, https://kakao.ai/product/minihexa
  10. 한국정보화진흥원, "인공지능 기반 챗봇 서비스의 국내외 동향분석 및 발전 전망," D. gov Trend & Future, 2018-2호, 2018.
  11. Z. Zhang et al., "Recent advances and challenges in task-oriented dialog systems," Sci. China Inf. Sci. May. 2020, arXiv: 2003.07490.
  12. H. Lee, J. Lee, and T. Y. Kim , "SUMBT: Slot-utterance matching for universal and scalable belief tracking," in Proc. Assoc. Comput. Linguist. 2019, pp. 5478-5483.
  13. M. Heck et al., "TripPy: A triple copy strategy for value independent neural dialog state tracking," in Proc. Spec. Interest Group Discourse. Dialogue. July. 2020, pp. 35-44.
  14. T. Zhao, K. Xie, and M. Eskenazi, "Rethinking action spaces for reinforcement learning in end-to-end dialog agents with latent variable models," in Proc. Conf. North Am. Chapter Assoc. Comput. Linguist.: Hum. Lang. Technol. Minneapolis, Minnesota, Apr. 2019, pp. 1208-1218.
  15. W. Chen et al., "Semantically conditioned dialog response generation via hierarchical disentangled self-attention," in Proc. Assoc. Comput. Linguist. Florence, Italy, Jan. 2019, pp. 3696-3709.
  16. W. Lei et al., "Sequicity: Simplifying task-oriented dialogue systems with single sequence-to-sequence architectures," in Proc. Assoc. Comput. Linguist. Melbourne, Australia, July. 2018, pp. 1437-1447.
  17. Y. Zhang, Z. Ou and Z. Yu, "Task-oriented dialog systems that consider multiple appropriate responses under the same context," in Proc. AAAI Conf. Aritif. Intell. Palo Alto, CA. USA. vol. 34 no. 5, 2019, pp. 9604-9611.
  18. A. Radford et al., "Language models are unsupervised multitask learners," OpenAI Technical Report, 2019, pp. 9604-9611.
  19. E. Hosseini-Asl et al., "A simple language model for task-oriented dialogue," in Proc. Conf. Neural Inform. Process. Syst. Vancouver, Canada, Dec. 2020.
  20. D. Ham et al., "End-to-end neural pipeline for goal-oriented dialogue systems using GPT2," in Proc. Assoc. Comput. Linguist. July. 2020, pp. 583-592.
  21. A. Bordes, Y. L. Boureau, and J. Weston, "Learning end-to-end goal-oriented dialog," in Proc. Int. Conf. Learn. Representations. Toulon, France, Apr. 2017, arXiv: 1605.07683v4
  22. A. Madotto, C. S. Wu, and P. Fung, "Mem2Seq: Effectively incorporating knowledge bases into end-to-end task-oriented dialog systems," in Proc. Assoc. Comput. Linguist. Melbourne, Australia, July. 2018, pp. 1468-1478.
  23. T. Wen et al., "Latent intention dialogue models," in Proc. Int. Conf. Mach. Learn. Sydney, Australia, Aug. 2017.
  24. Y. Zhang et al., "A probabilistic end-to-end task-oriented dialog model with latent belief states towards semi-supervised learning," in Proc. Conf. Empir. Methods. Natural Lang. Process. Nov. 2020, pp. 9207-9219.
  25. X. Li et al., "End-to-end task-completion neural dialogue systems," in Proc. Int. Conf. Natural Lang. Process. Taipei, Taiwan, Nov. 2017, pp. 733-743.
  26. T. Hong et al., "An end-to-end trainable task-oriented dialog system with human feedback," in Proc. AAAI Reason. Learn. Hum.-Mach. Dialogues. Honolulu, HI, USA, Jan. 2019, pp. 1-7.
  27. B. Liu and I. Lane, "Iterative policy learning in end-to-end trainable task-oriented neural dialog models," in Proc. Automat. Speech. Recognition. Underst. Workshop. Okinawa, Japan, Dec. 2017, pp. 482-489.
  28. A. Papangelis et al., "Collaborative multi-agent dialogue model training via reinforcement learning," in Proc. Spec. Interest Group Discourse. Dialogue. Stockholm, Sweden, Sept. 2019, pp. 92-102.
  29. R. Takanobu et al., "Multi-agent task-oriented dialog policy learning with role-aware reward decomposition," in Proc. Assoc. Comput. Linguist. 2020, pp. 625-638.
  30. S. Zhang et al., "Personalizing dialogue agents: I have a dog, do you have pets too?," in Proc. Assoc. Comput. Linguist. Melbourne, Australia, July. 2018, pp. 2204-2213.
  31. E. Dinan et al., "Wizard of wikipedia: Knowledge-powered conversational agents," in Proc. Int. Conf. Learn. Representations. New Orleans, LA, United States, May. 2019.
  32. D. Adiwardana et al., "Towards a human-like open-domain chatbot," 2020, arXiv: 2001.09977
  33. S. Roller et al., "Recipes for building an open-domain chatbot," 2020, arXiv: 2004.13637
  34. A. Vaswani et al., "Attention is all you need", in Proc. Int. Conf. Neural Inform. Process. Syst., Long Beach, CA, USA, Dec. 2017, pp. 6000-6010.
  35. Y. Zhang et al., "DialoGPT: Large-scale generative pre-training for conversational response generation," in Proc. Assoc. Comput. Linguist. July. 2020, pp. 270-278.
  36. T. B. Brown et al., "Language models are few-shot learners", in Proc. Conf. Neural Inform. Process. Syst. Vancouver, Canada, Dec. 2020.
  37. J. Devlin et al., "BERT: Pre-training of deep bidirectional transformers for language understanding," in Proc. Conf. North Am. Chapter Assoc. Comput. Linguist.: Hum. Lang. Technol. Minneapolis, Minnesota, June. 2019, pp. 4171-4186.
  38. D. R. So et al., "The evolved transformer," in Proc. Int. Conf. Mach. Learn. Long Beach, CA, USA, June, 2019.
  39. S. Humeau et al., "Poly-encoders: Architectures and pretraining strategies for fast and accurate multi-sentence scoring," in Proc. Int. Conf. Learn. Representations, Aug. 2020.
  40. 김현기 외, "엑소브레인 한국어 분석 및 질의응답 기술의 개발 현황 및 고도화 계획," 정보과학회지, 2017. 8. pp. 51-56.
  41. https://ai.google.com/research/NaturalQuestions
  42. https://hotpotqa.github.io/
  43. https://allenai.org/data/arc
  44. http://exobrain.kr/
  45. https://aiopen.etri.re.kr/
  46. https://www.statista.com/
  47. https://omdia.tech.informa.com
  48. 한국인터넷진흥원, "가정용 스마트 기기의 개인정보 침해 사례 및 최근 동향," 해외 개인정보보호 동향 보고서, 2019. 11.
  49. https://medium.com/
  50. https://www.ciokorea.com/
  51. https://www.voicesummit.ai/
  52. L. Sheerman et al., "COVID-19 and the secret virtual assistants: the social weapons for a state of emergency," Emerald Open Research, 2020.