경제학 지식 분석을 위한 BERT 기반 관계추출 모델과 지식그래프
BERT based Relation Extraction Model and Knowledge Graph for Economic Knowledge Analysis
2
조회
0
다운로드
2
인용
0
참고문헌
키워드
초록
경제학 지식은 조직이 좀 더 데이터 기반의 의사 결정하도록 지원하는 분석, 데이터 마이닝, 데이터 시각화, 데이터 도구, 모델링, 인프라를 모두 포함한다. 빠르게 변해가는 사회에서 좀 더 과학적 방법으로 해답을 제시해줄 수 있다. 본 논문에서는 경제학 논문 텍스트에서 키워드 개체 추출 시스템과 관계 정보를 학습하고 예측할 수 있는 관계 기반 BERT 모델을 제안한다. 관계 기반 BERT 모델을 실험을 통해 검증한 후에 지식 그래프 추출 및 지식 그래프 기반 의미론적 추론을 제시한다. 그래프의 연결성은 직접 연결된 관계 정보뿐 아니라 간접적으로 관련된 개체들을 통해 개념이 연결되어 문서 간의 잠재적인 숨겨진 관계를 드러낼 수 있다. 본 논문은 간접적인 관계 정보의 추출을 통해 새로운 의미 정보, 관계 정보를 추론하는 데 나아가는 연구의 방향성을 제시한다.
Abstract
Economic knowledge includes all analytics, data mining, data visualization, data tools, modeling, and infrastructure that help organizations make more data-driven decisions. In a rapidly changing society, solutions can be presented in a more scientific way. In this paper, we propose a relationship-based BERT model that can learn and predict keyword (entity) extraction systems and relationship information from the text of an economics paper. We present knowledge graph extraction and knowledge graph-based semantic inference after experimental validation of the relationship-based BERT model. The connectivity of graphs can reveal potential hidden relationships between documents by linking concepts through indirectly related objects as well as directly linked relationship information. This paper presents the direction of research moving forward to infer new semantic information and relational information through the extraction of indirect relational information.
참고문헌 (39)
- Vaswani, Ashish, "Attention Is All You Need", Proc. of the 31st International Conference on Neural Information Processing Systems (2017)
- Lewis, Mike, "Bart: Denoising Sequenceto-Sequence Pre-Training for Natural Language Generation, Translation, and Comprehension" (2020), ACL Anthology
- Zolnoori, Maryam, "A Systematic Approach for Developing a Corpus of Patient Reported Adverse Drug Events:: A Case Study for Ssri and Snri Medications", Journal of Biomedical Informatics, 90 (2019)
- Krebs, Alicia, "SemEval-2018 Task 10:Capturing Discriminative Attributes", Proc. of the 12th Intl. Workshop on Semantic Evaluation, pp.732~740 (2018)
- Hendrickx, Iris, "SemEval-2010 Task 8:Multi-Way Classification of Semantic Relations between Pairs of Nominals", Proc. of the 5th Intl. Workshop on Semantic Evaluation, pp.33~38 (2010)
- Zhou, GuoDong, "Exploring Various Knowledge in Relation Extraction", Proc. of the 43rd Annual Meeting of the Association for Computational Linguistics (ACL’05), pp.427~434 (2005)
- J. Jiang, "A Systematic Exploration of the Feature Space for Relation Extraction", Human Language Technologies 2007: The Conference of the North American Chapter of the Association for Computational Linguistics; Proc. of the Main Conference, pp.113~120 (2007)
- R. Bunescu, "A Shortest Path Dependency Kernel for Relation Extraction", Proc. of Human Language Technology Conference and Conference on Empirical Methods in Natural Language Processing, pp.724~731 (2005)
- Qian, Longhua, "Exploiting Constituent Dependencies for Tree Kernel-Based Semantic Relation Extraction", Proc. of the 22nd Intl. Conference on Computational Linguistics (Coling 2008), pp.697~704 (2008)
- Pawar, Sachin, "End-to-end Relation Extraction using Neural Networks and Markov Logic Networks", Proc. of the 15th Conference of the European Chapter of the Association for Computational Linguistics, 1, pp.818~827 (2017)
- Zhong, Cheng, "Hierarchical reinforcement learning for automatic disease diagnosis", Bioinformatics, 38(16), pp.3995~4001 (2022)
- Li, Qian, "Reinforcement Learning-Based Dialogue Guided Event Extraction to Exploit Argument Relations", IEEE, 2022, pp.30, 520~533
- D. Martinez, "Knowledge Base Development", Proc. of Intl. Conference on Knowledge-Based and Intelligent Information and Engineering Systems, pp.1373~1380 (2003)
- Ling, Yuan, "Integrating extra knowledge into word embedding models for biomedical NLP tasks", Proc. of Intl. Joint Conference on Neural Networks (IJCNN) (2017)
- Zhong, Haoxi, "How Does NLP Benefit Legal System: A Summary of Legal Artificial Intelligence", Proc.of the 58th Annual Meeting of the Association for Computational Linguistics, pp.5218~5230 (2020)
- B. Yang, "Leveraging Knowledge Bases in LSTMs for Improving Machine Reading", Proc. of the 55th Annual Meeting of the Association for Computational Linguistics, 1, pp.1436~1446 (2017)
- Zhang, Zhengyan, "ERNIE: Enhanced Language Representation with Informative Entities", Proc. of the 57th Annual Meeting of the Association for Computational Linguistics, pp.1441~1451 (2019)
- Liu, Mengwen, "Relation extraction from biomedical literature with minimal supervision and grouping strategy", Proc. of IEEE Intl. ,l'(BIBM), pp.444~449 (2014)
- Zhong, Haoxi, "How Does NLP Benefit Legal System: A Summary of Legal Artificial Intelligence", Proc. of the 58th Annual Meeting of the Association for Computational Linguistics, pp.218~5230 (2020)
- Choi, Eunsol, "Ultra Fine Entity Typing", Proc. of the 56th Annual Meeting of the Association for Computational Linguistics, 1, pp.87~96 (2018)
- Han, Xu, "Fewrel : A large scale supervised few shot relation classification dataset with state of the art evaluation", Proc. of the 2018 Conference on Empirical Methods in Natural Language Processing, pp.4803~4809 (2018)
- Logan, Robert, "Barack’s Wife Hillary:Using Knowledge Graphs for Fact-Aware Language Modeling", Proc. of the 57th Annual Meeting of the Association for Computational Linguistics, pp.5962~5971 (2019)
- Peters, Matthew E., "Knowledge Enhanced Contextual Word Representations", Proc.of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th Intl. Joint Conference on Natural Language Processing(EMNLP-IJCNLP), pp.43~54 (2019)
- Hogan, Aidan, "Knowledge Graphs", ACM Comput. Surv, 54(4), pp.1~37 (2021)
- S. Hochreiter, "Long short-term memory", Neural Computation, 9(8), pp.1735~1780 (1997)
- D. E. Rumelhart, "Book Chapter: Parallel Distributed Processing:Explorations in the Microstructure of Cognition:Foundations", pp.318~362 (1985), MIT Press
- Peters, Matthew E., "Deep contextualized word representations", Proc. of the 2018Conference of the North American Chapter of the Association for Computational Linguistics:Human Language Technologies, 1, pp.2227~2237 (2018)
- Brown, Tom, "Language models are few-shot learners", Proc. of Neural Information Processing Systems, 33 (2020)
- Kim, Soojeong, "Keyword Extraction in Economics Literatures using Natural Language Processing", Proc. Of Intl. Conference on Ubiquitous and Future Networks(ICUFN) (2021)
- Soares, L. Baldini, "Matching the Blanks:Distributional Similarity for Relation Learning", Proc. of the 57th Annual Meeting of the Association for Computational Linguistics, pp.2895~2905 (2019)
- Zhao, Kang, "Representation iterative fusion based on heterogeneous graph neural network for joint entity and relation extraction", Knowledge-Based Systems, 219(11) (2021)