大模型与知识图谱(Large Language Models and Knowledge Graphs)
Yubo Chen (玉博 陈), Shaoru Guo (少茹 郭), Kang Liu (康 刘), Jun Zhao (军 赵)
Abstract
“知识图谱作为一种重要的知识组织形式,常被视为下一代人工智能技术的基础设施之一,引起了工业界和学术界的广泛关注。传统知识图谱表示方法主要使用符号显式地描述概念及其之间的结构关系,具有语义清晰和可解释性好等特点,但其知识类型有限,难以应对开放域应用场景。随着大规模预训练语言模型(大模型)的发展,将参数化的大模型视为知识图谱成为研究热点。在这一背景下,本文聚焦于大模型在知识图谱生命周期中的研究,总结分析了大模型在知识建模、知识获取、知识融合、知识管理、知识推理和知识应用等环节中的研究进展。最后,对大模型与知识图谱未来发展趋势予以展望。”- Anthology ID:
- 2023.ccl-2.6
- Volume:
- Proceedings of the 22nd Chinese National Conference on Computational Linguistics (Volume 2: Frontier Forum)
- Month:
- August
- Year:
- 2023
- Address:
- Harbin, China
- Editor:
- Jiajun Zhang
- Venue:
- CCL
- SIG:
- Publisher:
- Chinese Information Processing Society of China
- Note:
- Pages:
- 67–76
- Language:
- Chinese
- URL:
- https://aclanthology.org/2023.ccl-2.6
- DOI:
- Cite (ACL):
- Yubo Chen, Shaoru Guo, Kang Liu, and Jun Zhao. 2023. 大模型与知识图谱(Large Language Models and Knowledge Graphs). In Proceedings of the 22nd Chinese National Conference on Computational Linguistics (Volume 2: Frontier Forum), pages 67–76, Harbin, China. Chinese Information Processing Society of China.
- Cite (Informal):
- 大模型与知识图谱(Large Language Models and Knowledge Graphs) (Chen et al., CCL 2023)
- PDF:
- https://preview.aclanthology.org/proper-vol2-ingestion/2023.ccl-2.6.pdf