EUVIMEDEUVIMED entdecken
Crossref

CodeKGC: Code Language Model for Generative Knowledge Graph Construction

Zhen Bi, Jing Chen, Yinuo Jiang, Feiyu Xiong, Wei Guo, Huajun Chen, Ningyu Zhang

ACM Transactions on Asian and Low-Resource Language Information Processing · 31.03.2024 · 23 (3) · 1-16

DOI: 10.1145/3641850 ↗

Kurz gefasst

Fachartikel in der Zeitschrift ACM Transactions on Asian and Low-Resource Language Information Processing, online erschienen am 09.03.2024. Verfasst von Zhen Bi und 6 weiteren Autor:innen. Die Arbeit wurde bisher 76-mal zitiert (Crossref) und nennt 38 Literaturangaben. Gefördert von: National Natural Science Foundation of China, Fundamental Research Funds for the Central Universities, Zhejiang Provincial Natural Science Foundation of China.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Current generative knowledge graph construction approaches usually fail to capture structural knowledge by simply flattening natural language into serialized texts or a specification language. However, large generative language model trained on structured data such as code has demonstrated impressive capability in understanding natural language for structural prediction and reasoning tasks. Intuitively, we address the task of generative knowledge graph construction with code language model: given a code-format natural language input, the target is to generate triples which can be represented as code completion tasks. Specifically, we develop schema-aware prompts that effectively utilize the semantic structure within the knowledge graph. As code inherently possesses structure, such as class and function definitions, it serves as a useful model for prior semantic structural knowledge. Furthermore, we employ a rationale-enhanced generation method to boost the performance. Rationales provide intermediate steps, thereby improving knowledge extraction abilities. Experimental results indicate that the proposed approach can obtain better performance on benchmark datasets compared with baselines. 1

Förderung

  • National Natural Science Foundation of China
  • Fundamental Research Funds for the Central Universities
  • Zhejiang Provincial Natural Science Foundation of China
  • Ningbo Natural Science Foundation
  • CAAI-Huawei MindSpore Open Fund, Yongjiang Talent Introduction Programme
  • CCF-Baidu Open Fund
  • Information Technology Center and State Key Lab of CAD&CG, Zhejiang University

Zitieren

APA

Bi, Z., Chen, J., Jiang, Y., Xiong, F., Guo, W., Chen, H., & Zhang, N. (2024). CodeKGC: Code Language Model for Generative Knowledge Graph Construction. ACM Transactions on Asian and Low-Resource Language Information Processing, 23(3), 1-16. https://doi.org/10.1145/3641850

Vancouver

Bi Z, Chen J, Jiang Y, Xiong F, Guo W, Chen H, et al. CodeKGC: Code Language Model for Generative Knowledge Graph Construction. ACM Transactions on Asian and Low-Resource Language Information Processing. 2024;23(3):1-16. doi:10.1145/3641850

BibTeX
@article{Bi2024,
  author = {Bi, Zhen and Chen, Jing and Jiang, Yinuo and Xiong, Feiyu and Guo, Wei and Chen, Huajun and Zhang, Ningyu},
  title = {CodeKGC: Code Language Model for Generative Knowledge Graph Construction},
  journal = {ACM Transactions on Asian and Low-Resource Language Information Processing},
  year = {2024},
  volume = {23},
  number = {3},
  pages = {1--16},
  doi = {10.1145/3641850}
}
Kostenlos starten →