한국컴퓨터정보학회논문지 (Journal of the Korea Society of Computer and Information)

  • 제25권4호
  • /
  • Pages.11-17
  • /
  • 2020
  • /
  • 1598-849X(pISSN)
  • /
  • 2383-9945(eISSN)
한국컴퓨터정보학회 (Korean Society of Computer Information)
권호 표지
DOI QR코드

DOI QR Code

A Study on Building Knowledge Base for Intelligent Battlefield Awareness Service

  • 투고 : 2020.03.19
  • 심사 : 2020.04.06
  • 발행 : 2020.04.29
PDF 다운로드
⟨ 이전 논문 다음 논문 ⟩

초록

본 논문에서는 지능형 전장인식 서비스를 위한 자연어처리 기반 지식베이스 구축 방안에 대해 연구한다. 현재의 지휘통제체계는 수집된 전장정보와 전술데이터를 등록, 저장, 공유 등의 기본적인 수준에서 관리 및 활용하고 있으며, 분석관에 의한 정보/데이터 융합 및 상황 분석/판단이 수행되고 있다. 이는 분석가의 시간적 제약과 인지적 한계로 일반적으로 하나의 해석만이 도출되며 편향된 사고가 반영될 수 있다. 따라서 지휘통제체계의 전장상황인식 및 지휘결심지원 지능화가 필수적이다. 이를 위해서는 지휘통제체계에 특화된 지식베이스를 구축하고 이를 기반으로 하는 지능형 전장인식 서비스 개발이 선행되어야 한다. 본 논문에서는, 민간 데이터인 엑소브레인 말뭉치에서 제시된 개체명 중 의미 있는 상위 250개 타입을 적용하고 전장정보를 적절히 표현하기 위해 무기체계 개체명 타입을 추가 식별하였다. 이를 바탕으로 멘션 추출, 상호참조해결 및 관계 추출 과정을 거치는 전장인식 지식베이스 구축 방안을 제시하였다.

In this paper, we propose a method to build a knowledge base based on natural language processing for intelligent battlefield awareness service. The current command and control system manages and utilizes the collected battlefield information and tactical data at a basic level such as registration, storage, and sharing, and information fusion and situation analysis by an analyst is performed. This is an analyst's temporal constraints and cognitive limitations, and generally only one interpretation is drawn, and biased thinking can be reflected. Therefore, it is essential to aware the battlefield situation of the command and control system and to establish the intellignet decision support system. To do this, it is necessary to build a knowledge base specialized in the command and control system and develop intelligent battlefield awareness services based on it. In this paper, among the entity names suggested in the exobrain corpus, which is the private data, the top 250 types of meaningful names were applied and the weapon system entity type was additionally identified to properly represent battlefield information. Based on this, we proposed a way to build a battlefield-aware knowledge base through mention extraction, cross-reference resolution, and relationship extraction.

키워드

참고문헌

  1. Jhchung, "Support for military decision-making AI Possibility and preparation for implementation," ETRI Insight Report 2019-38, pp. 1-10, 2019.
  2. Djlee, Tkkim, Jkhan, Dhjegal, "Development plan of AI and M&S based command decision support system," Defense & Technology, No. 456, pp. 66-79, February 2017.
  3. Jykim, Khro, "Construction of Knowledge Base Based on Graph Database for College Student Career Advice Using Public Data," Journal of The Institute of Electronics and Information Engineers, pp. 41-48, October 2019. DOI: 10.5573/ieie.2019.56.10.41
  4. Gwhong, Shmyaeng, "Generation of open relation embeddings from natural language sentences using BERT and knowledge base relation embeddings," Journal of The Korean Institute of Information Scientists and Engineers, pp. 533-535, ICC JEJU, Korea, June 2019.
  5. Jhkim, Mjlee, "Knowledge Extraction Methodology and Framework from Wikipedia Articles for Construction of Knowledge-Base," Journal of Intelligence and Information Systems, pp. 43-61, March 2019. DOI: 10.13088/jiis.2019.25.1.043
  6. Swjung, Mschoi, Hskim, "Construction of Korean Knowledge Base Based on Machine Learning from Wikipedia," Journal of KIISE, Vol. 42, No. 8, pp. 1065-1070, August 2015. DOI: 10.5626/JOK.2015.42.8. 1065
  7. G. Lample, M. Ballesteros, S. Subramanian, K. Kawakami, and C. Dyer, "Neural architectures for named entity recognition," AarXiv preprint arXiv:1603.01360, March 2016.
  8. Yhshin, Sglee, "Bidirectional LSTM-RNNs-CRF for Named Entity Recognition in Korean," Journal of Korean Language Information Science Society, pp. 340-341, Donga Univ., Korea, October 2016.
  9. Cysong, Smyang, Swkang, "Named-entity Recognition Using Bidirectional LSTM CRFs," Journal of Korean Language Information Science Society, pp. 321-323, daegu catholic univ., Korea, October 2017.
  10. Zhiheng Huang, Wei Xu, Kai Yu, "Bidirectional LSTM-CRF Models for Sequence Tagging," arXiv preprint arXiv:1508.01991, 2015.
  11. A. Radford, K. Narasimhan, T. Salimans, and I. Sutskever, "Improving language understanding by generative pretraining," Technical report, OpenAI, 2018.
  12. M. E. Peters, M. Neumann, M. Iyyer, M. Gardner, C. Clark, K. Lee, and L. Zettlemoyer, "Deep contextualized word representations," arXiv preprint arXiv:1802.05365, 2018.
  13. Devlin, Jacob, et al. "Bert: Pre-training of deep bidirectional transformers for language understanding." arXiv preprint arXiv:1810.04805, 2018.
  14. Swjeong, Mschoi, Hskim, "Coreference Resolution for Korean Using Random Forests," Journal of KTSDE, Vol. 5, No. 11, pp. 535-540, 2016. DOI: 10.3745/KTSDE.2016. 5.11.535
  15. Shnam, Kjhan, Ekkim, Sgkwon, Ysjung, Kschoi, "Multi-sense Word Embedding to Improve Performance of a CNN-based Relation Extraction Model," Journal of KIISE, Vol. 45, No. 8, pp. 816-824. 2018. DOI: 10.5626/JOK.2018.45.8.816
  16. Sspark, Hskim. "Relation Extraction among Multiple Entities using Dual-Pointer Network," Journal of KIISE, Vol. 46, No. 11, pp. 1186-1192. 2019. DOI: 10.5626/JOK.2019.46.11.1186