DOI QR코드

DOI QR Code

Keyword Retrieval-Based Korean Text Command System Using Morphological Analyzer

형태소 분석기를 이용한 키워드 검색 기반 한국어 텍스트 명령 시스템

  • Park, Dae-Geun (Department of Game Design, Kongju National University) ;
  • Lee, Wan-Bok (Department of Game Design, Kongju National University)
  • 박대근 (공주대학교 게임디자인학과) ;
  • 이완복 (공주대학교 게임디자인학과)
  • Received : 2018.11.20
  • Accepted : 2019.02.20
  • Published : 2019.02.28

Abstract

Based on deep learning technology, speech recognition method has began to be applied to commercial products, but it is still difficult to be used in the area of VR contents, since there is no easy and efficient way to process the recognized text after the speech recognition module. In this paper, we propose a Korean Language Command System, which can efficiently recognize and respond to Korean speech commands. The system consists of two components. One is a morphological analyzer to analyze sentence morphemes and the other is a retrieval based model which is usually used to develop a chatbot system. Experimental results shows that the proposed system requires only 16% commands to achieve the same level of performance when compared with the conventional string comparison method. Furthermore, when working with Google Cloud Speech module, it revealed 60.1% of success rate. Experimental results show that the proposed system is more efficient than the conventional string comparison method.

딥러닝을 기반으로 한 음성 인식 기술이 상용 제품에 적용되기 시작했지만, 음성 인식으로 분석된 텍스트를 효율적으로 처리할 방법이 없기 때문에 VR 컨텐츠에서 그 적용 예를 찾아 보기는 쉽지 않다. 본 논문은 문장의 형태소를 분석하는 형태소 분석기와 챗봇 개발에 주로 이용되는 검색 기반 모델(Retrieval-Based Model)을 활용하여 명령어를 효율적으로 인식하고 대응할 수 있는 한국어 텍스트 명령 시스템을 제안하는 것을 목적으로 한다. 실험 결과 제안한 시스템은 문자열 비교 방식과 같은 동작을 하기 위해 16%의 명령어만 필요했으며, Google Cloud Speech와 연동하였을 때 60.1%의 성공률을 보였다. 실험 결과를 통해 제안한 시스템이 문자열 비교 방식보다 효율적이라는 것을 알 수 있다.

Keywords

OHHGBW_2019_v10n2_159_f0001.png 이미지

Fig. 1. Market Outlook

OHHGBW_2019_v10n2_159_f0002.png 이미지

Fig. 2. The process of registering a skill

OHHGBW_2019_v10n2_159_f0003.png 이미지

Fig. 3. Flowchart of Korean text command system

OHHGBW_2019_v10n2_159_f0004.png 이미지

Fig. 4. Flowchart of Korean text command system

OHHGBW_2019_v10n2_159_f0005.png 이미지

Fig. 5. Comparison of dictionary design methods

OHHGBW_2019_v10n2_159_f0006.png 이미지

Fig. 6. Postpositions

OHHGBW_2019_v10n2_159_f0007.png 이미지

Fig. 7. Keyword extraction result

OHHGBW_2019_v10n2_159_f0008.png 이미지

Fig. 8. Command search process flowchart

OHHGBW_2019_v10n2_159_f0009.png 이미지

Fig. 9. Command Search Result

OHHGBW_2019_v10n2_159_f0010.png 이미지

Fig. 10. Action pseudocode

OHHGBW_2019_v10n2_159_f0011.png 이미지

Fig. 11. Unity3D 2017.4.2.f2

OHHGBW_2019_v10n2_159_f0012.png 이미지

Fig. 12. Action pseudocode

OHHGBW_2019_v10n2_159_f0013.png 이미지

Fig. 13. Recognized command and registered command

References

  1. Hebronstar. (2018). VR/AR Trends. Hebronstar [Online], http://hebronstar.com/?p=6272.
  2. K. U. Han & H. T. Kim. (2011). The Cause and Solution of Cybersickness in 3D Virtual Environments. Korean Journal of Cognitive and Biological Psychology. 23(2). 287-299. https://doi.org/10.22172/cogbio.2011.23.2.007
  3. J. Y. Jumg, K. S. Cho, J. H. Choi & J. H. Choi. (2017). Causes of Cyber Sickness of VR Contents - An Experimental Study on the Viewpoint and Movement. The Korea Contents Society. 17(4). 200-208.
  4. M. Y. Choi & S. W. Kim. (2016). EA Study on the First Use Experience for Rapid Adaptation to HMD VR Contents -Focused on Samsung Gear VR Game Application-. Korean Society of Basic Design & Art. 17(6). 605-616.
  5. J. W. Park & S. K. No. (2018). EA Study on the Structural Features of VR HMD Interface Design -Focused Oculus Home -. The Korean Society Of Design Culture. 37. 78-87.
  6. J. Y. Han. (2016). Study on the Feature of Mobile HMD-Based VR Experience Contents Design. Korean Institute of Spatial Design. 37(0). 78-87.
  7. O. T. Kim. (2010). The Impact of Video Game's Controller Realism on Natural Mapping, Spatial Presence, Arousal and Emotions: Using First-Person Shooting Video Games. korean society for journalism and communication studies. 54(5). 227-253.
  8. E. J. Hong, K. S. Cho & J. H. Choi. (2017). Effects of Anthropomorphic Conversational Interface for Smart Home:An Experimental Study on the Voice and Chatting Interactions. HCI Society of Korea. 12(1). 15-23. https://doi.org/10.17210/jhsk.2017.02.12.1.15
  9. J. H. Choi & S. H. Lee. (2017). 음Current status and implications of voice recognition AI secretary market. Korea Association for Telecommunications Polices. 29(9). 1-37.
  10. S. R. Jung. (2018). Analysis of promising technologies based on artificial intelligence through patent search. Master dissertation. Korea University. Seoul.
  11. E. J. Park & S. Z. Cho. (2014). KoNLPy: Korean natural language processing in Python. HCLT. 26. 133-136.
  12. Jack Cahn. (2017). CHATBOT: Architecture, Design, & Development. Senior Thesis. University of Pennsylvania. Pennsylvania.
  13. Rob High. (2012). The Era of Cognitive Systems: An Inside Look at IBM Watson and How it Works. Armonk : IBM RedBooks.
  14. J. Weizenbaum. (1996). ELIZA-A computer program for he study of natural language communication be-tween man can machine. Communications of the Association for Computing Machinery. 9(1). 36-46. https://doi.org/10.1145/365153.365168
  15. B. P. Schumaker, Ying Liu, Mark Ginsburg & Hsinchun Chen. (2006). Evaluating mass knowledge ac-quisition using the ALICE chatterbot: the AZ-ALICE dialog system. International Journal of Human-Computer Studies. 64(11). 1132-1140. https://doi.org/10.1016/j.ijhcs.2006.06.008