Annual Conference of KIPS (한국정보처리학회:학술대회논문집)

  • 2024.10a
  • /
  • Pages.805-808
  • /
  • 2024
  • /
  • 2005-0011(pISSN)
  • /
  • 2671-7298(eISSN)
Korea Information Processing Society (한국정보처리학회)
권호 표지
DOI QR코드

DOI QR Code

Prompt Engineering automated Knowledge Unit processing

프롬프트 엔지니어링을 이용한 자동화된 지식 유닛 처리

  • Mira Mauleshova (System Engineering Department Czech University of Life Sciences) ;
  • Milan Houska (System Engineering Department Czech University of Life Sciences) ;
  • Shivani Kolekar (Dept. of Artificial Intelligence Convergence, Chonnam National University) ;
  • Kyungbaek Kim (Dept. of Artificial Intelligence Convergence, Chonnam National University)
  • 미라 마울레쇼바 (체코 생명과학대학교 시스템 공학과) ;
  • 밀란 후슈카 (체코 생명과학대학교 시스템 공학과) ;
  • 시바니 산제이 콜레카르 (전남대학교 인공지능학과) ;
  • 김경백 (전남대학교 인공지능학과)
  • Published : 2024.10.31
Download PDF
⟨ Previous Next ⟩

Abstract

This paper is dedicated to automated Knowledge Unit extraction by employing Prompt Engineering within the Generative AI models. The experiment is conducted analyzing the ability of GPT-4 to extract Knowledge Units' elements in an automated manner by the created prompts. Verification is proceeded by comparison among results from GPT-4 and the elements of Knowledge Units coming from the original methodology of knowledge-structured texts' creation. The results of the research prove that thanks to the created prompts, Knowledge Units are successfully extracted from unstructured text.

Keywords

Acknowledgement

This work was supported by Innovative Human Resource Development for Local Intellectualization program through the Institute of Information & Communications Technology Planning & Evaluation(IITP) grant funded by the Korea government(MSIT)(IITP-2024-RS-2022-00156287, 50%). This work was supported by Institute of Information & communications Technology Planning & Evaluation (IITP) under the Artificial Intelligence Convergence Innovation Human Resources Development (IITP-2023-RS-2023-00256629, 50%) grant funded by the Korea government(MSIT).

References

  1. Vaidya, Madhavi, Katkar, Shweta. 2022. Exploring performance and predictive analytics of agriculture data. AI, Edge and IoT-based Smart Agriculture. pp. 409-436. ISBN 9780128236949 
  2. Marik, Vladimir. 1997. Umela inteligence 2. Prague: Academia. ISBN 80-200-0504-8. 11 
  3. Choi, Jaewoong, Lee, Byungj. 2024. "Accelerating Materials Language Processing with Large Language Models." Communications Materials 5(1). doi: 10.1038/s43246-024-00449-9. 
  4. Brozova, Helena, Houska, Milan et al. 2011. Modelovani znalosti. Prague: Professional Publishing. ISBN 978-80-7431-069-0 
  5. CORTICAL.IO. ©2022. Business. Cortical.io. [online]. [cit. 2023-02-07]. Available from: https://www.cortical.io/blog/4-things-you-should-know-about-unstructured-text/ 
  6. Jouffroy, Jordan, Feldman, Sarah, Lerner, Ivan, Rance, Bastien, Burgun, Anita, Nauraz, Antoine. 2021. Hybrid Deep Learning for Medication - Related Information Extraction from Clinical Texts in French: MedExt Algorithm Development Study. JMIR Medical Informatics. Vol. 9 (3). DOI: 10.2196/17934 
  7. Steinkamp, Jackson, Bala, Wasif, Sharma, Abhinav, Kantrowitz, Jacob. 2020. Task definition, annotated dataset, and supervised natural language processing models from symptom extraction from unstructured clinical notes. Journal of Biomedical Informatics. Vol. 102. DOI: 10.1016/j.jbi.2019.103354. 
  8. Manesh, Batta. 2018. Machine learning algorithms - A Review. International Journal of Science and Research (IJSR). Vol. 18, Issue 8. DOI: 10.21275/ART20203995 
  9. Maitra, Anutosh, Garg, Shivam, Sengupta, Shubhashis. 2020. Enabling Interactive Answering of Procedural Questions. Natural Language Processing and Information Systems. Lecture Notes in Computer Science(), vol 12089. Springer, Cham. DOI: 10.1007/978-3-030-51310-8_7 
  10. Qiu, Qinjun, Xie, Zhong, Wu, Liang, Tao, Liufeng. 2020. Automatic spatiotemporal and semantic information extraction from unstructured geoscience reports using text mining techniques. Earth Science Informatics. Vom. 13, 1393-1410. DOI: https://doi.org/10.1007/s12145-020-00527-9 
  11. Houskova Berankova, Martina, Mudrychova, Kristyna, Petak, Michal, Horakova, Tereza, Houska, Milan. 2021. Metodika tvorby znalostne strukturovanych textu [Methodology of creating knowledge-structured texts]. E - Approved Methodology (NmetS), ISBN 978-80-213-3120-4, Agreement on the application of the methodology with Ceska posta s.p., closing date 4/1/2021. C - The result is use without restrictions on the range of users, Ministry of Labor and Social Affairs, 14/06/2021. 
  12. IBM.com ©2024. What is prompt engineering?. IBM.com. [online]. [cit. 2024-06-13]. Available from: What Is Prompt Engineering? | IBM 
  13. Xiao, Zhengyang, Li, Weny, Moon, Hannah, Roell, Garrett, Chen, Yixin, Tang, Yinjie. 2023. "Generative Artificial Intelligence GPT-4 Accelerates Knowledge Mining and Machine Learning for Synthetic Biology." ACS Synthetic Biology 12(10):2973 - 2982. doi: 10.1021/acssynbio.3c00310 
  14. Scheepens, Daan, Milliard, Josep, Farrell, Maxwel, Newbold, Tim. 2024. "Large Language Models Help Facilitate the Automated Synthesis of Information on Potential Pest Controllers." Methods in Ecology and Evolution. doi: 10.1111/2041-210X.14341. 
  15. OpenAI.com. 2023. GPT-4. Openai.com. [online]. [cit. 2024-06-13]. Available from: GPT-4 | OpenAI