The Transactions of the Korea Information Processing Society (정보처리학회 논문지)

Korea Information Processing Society (한국정보처리학회)
권호 표지
DOI QR코드

DOI QR Code

3D Object State Extraction Through Adjective Analysis from Informal Requirements Specs

비정형 요구사항 스펙에서 형용사 분석을 통한 3D 객체 상태 추출화

  • 진예진 (홍익대학교 소프트웨어공학연구실) ;
  • 서채연 (홍익대학교 소프트웨어융합학과 ) ;
  • 공지훈 (홍익대학교 소프트웨어공학연구실 ) ;
  • 김영철 (홍익대학교 소프트웨어융합학과 )
  • Received : 2024.07.31
  • Accepted : 2024.09.23
  • Published : 2024.10.31
Download PDF
⟨ Previous Next ⟩

Abstract

Recent advancements in AI technology have led to its application across various fields. However, the lack of transparency in AI operations makes it challenging to guarantee the quality of its outputs. Therefore, we integrate requirements engineering in software engineering with conversational AI technology to ensure procedural fairness. Traditional requirements engineering research uses grammar-centered analysis, which often fails to fully interpret the semantic aspects of natural language. To solve this, we suggest combining Noam Chomsky's syntactic structure analysis with Charles Fillmore's semantic role theory. Additionally, we extend our previous research by analyzing adjectives in informal requirement sentence structures. This enables precise emotional analysis of the main characters in comics. Based on the results of the analysis, we apply the emotional states of the objects to the states in the UML state diagram. Then, we create the 3D object with Three.js based on the object that reflects the emotional states in the state diagram. With this approach, we expect to represent the emotional state of a 3D object.

최근 AI 기술의 발전으로 다양한 분야에서 활용되고 있다. 그러나 AI의 동작 원리를 확인할 수 없어 생성물의 품질을 보장하기 어렵다. 따라서 본 연구에서는 대화형 AI 기술에 소프트웨어 공학의 요구공학을 접목하여 절차적 공정을 진행한다. 기존의 요구공학 연구는 문법 중심 분석 방식을 사용하여 비정형 요구사항의 의미적 측면을 충분히 해석하지 못하는 한계를 가진다. 이를 해결하기 위해, 우리는 촘스키의 구문 구조 분석 이론과 필모어의 의미역 이론의 통합을 제안한다. 또한, 우리는 이전 연구를 확장하여 다양한 문장 구조에서 사용되는 형용사 분석을 추가한다. 이는 만화 속 주인공에 대한 정확한 감정 분석이 가능하다. 분석 결과를 기반으로, 우리는 상태 다이어그램의 상태를 객체의 감정 상태로 적용한다. 우리는 객체의 상태 다이어그램의 감정 상태 기반으로 Three.js를 통해, 3D 객체 모델 생성과 와 상태를 표현시킨다. 이를 통해, 객체의 감정을 표현하기를 기대한다.

Keywords

Acknowledgement

This research was supported by Korea Creative Content Agency (KOCCA) grant funded by the Ministry of Culture, Sports and Tourism(MCST) in 2023(Project Name: Development of AI-based user interactive multimodal interactive storytelling 3D scene authoring technology, Project Number: RS-2023-00227917, Contribution Rate: 80%) and Basic Science Research Program through the National Research Foundation of Korea(NRF) funded by the Ministry of Education in 2023(Project Name: The Faultless Codinglization through Automatic Refactoring based on NLP BERT Model, Project Number: 2021R1I1A3050407, Contribution Rate: 10%) and BK21 FOUR (Fostering Outstanding Universities for Research) funded by the Ministry of Education (MOE, Korea) in 2023 (Project Number: 2021R1I1A305040711, Contribution Rate: 10%).

References

  1. J. Gao, C. Tao, D. Jie, and S. Lu, "What is AI software testing? and why," 2019 IEEE International Conference on Service-Oriented System Engineering (SOSE), IEEE, pp. 27-36, 2019. 
  2. Y. J. Jin, C. Y. Seo, and R. Y. C. Kim, "3D Object State Representation via State Diagram based on Informal Natural Language Requirement Specifications," Proceedings of the Annual Symposium of Korea Information Processing Society Conference (KIPS) 2024, Vol.31, pp.494-496, 2024. 
  3. Z. Feng, "Formal analysis for natural language processing: a handbook," Springer, pp.520-534, 2023. https://doi.org/10.1007/978-981-16-5172-4. 
  4. N. Chomsky, Syntactic structures, USA: Mouton de Gruyter, 2002. 
  5. Berkeley Neural Parser [Internet], https://parser.kitaev.io/. 
  6. C. J. Fillmore, "The Case for Case," New York: HR&W, 1968. 
  7. S. Kasper, "A comparison of 'thematic role' theories," 2008. doi:10.13140/2.1.1540.4805. 
  8. B. Das, M. Majumder, and S. Phadikar, "A novel system for generating simple sentences from complex and compound sentences," International Journal of Modern Education and Computer Science, Vol.11, No.1, pp.57-64, 2018. 
  9. B. K. Park and R. Y. C. Kim, "Effort estimation approach through extracting use cases via informal requirement specifications," Applied Sciences, Vol.10, No.9, 2020. doi:10.3390/app10093044 
  10. Meshy Documentation [Internet], https://docs.meshy.ai/. 
  11. Masterpiece X [Internet], https://www.masterpiecex.com/.