模式识别与人工智能
Monday, Apr. 7, 2025 Home      About Journal      Editorial Board      Instructions      Ethics Statement      Contact Us                   中文
Pattern Recognition and Artificial Intelligence  2024, Vol. 37 Issue (8): 715-728    DOI: 10.16451/j.cnki.issn1003-6059.202408005
Papers and Reports Current Issue| Next Issue| Archive| Adv Search |
Narrative-Driven Large Language Model for Temporal Knowledge Graph Prediction
CHEN Juan1,2, ZHAO Xinchao3, SUI Jingyan1,2, QI Lin4, TIAN Chen4, PANG Liang1,2, FANG Jinyun1
1. Prospective Research Laboratory, Institute of Computing Te-chnology, Chinese Academy of Sciences, Beijing 100190;
2. School of Computer Science and Technology, University of Chinese Academy of Sciences, Beijing 100049;
3. Landinn Center, Big Data Academy, Zhongke, Zhengzhou 450046;
4. School of Software Engineering, Beijing Jiaotong University, Beijing 100044

Download: PDF (1033 KB)   HTML (1 KB) 
Export: BibTeX | EndNote (RIS)      
Abstract  The temporal knowledge graph(TKG) is characterized by vast sparsity, and the long-tail distribution of entities leads to poor generalization in reasoning for out-of-distribution entities. Additionally, the low infrequency of historical interactions results in biased predictions for future events. Therefore, a narrative-driven large language model for TKG Prediction is proposed. The world knowledge and complex semantic reasoning capabilities of large language models are leveraged to enhance the understanding of out-of-distribution entities and the association of sparse interaction events. Firstly, a key event tree is selected based on the temporal and structural characteristics of TKG, and the most representative events are extracted through a historical event filtering strategy. Relevant historical information is summarized to reduce input data while the most important information is retained. Then, the large language model generator is fine-tuned to produce logically coherent "key event tree" narratives as unstructured input. During the generation process, special attention is paid to the causal relationships and temporal sequences of events to ensure the coherence and rationality of the generated stories. Finally, the large language model is utilized as a reasoner to infer the missing temporal entities. Experiments on three public datasets demonstrate that the proposed method effectively leverages the capabilities of large models to achieve more accurate temporal entity reasoning.
Key wordsTemporal Knowledge Graph(TKG)      Large Language Model      Key Event Tree      Temporal Story      Event Inference     
Received: 22 July 2024     
ZTFLH: TP391  
Corresponding Authors: PANG Liang, Ph.D., assistant professor. His research interests include natural language processing and machine learning.   
About author:: CHEN Juan, Ph.D.candidate. Her research interests include temporal knowledge graphs, large language models and natural language processing. ZHAO Xinchao, Master student. His research interests include natural language processing. SUI Jingyan, Ph.D.candidate. Her research interests include algorithm design, machine learning, deep learning and combinatorial optimization. QI Lin, Master student. Her research interests include graph neural networks and natural language processing.TIAN Chen, Master student. His research interests include graph neural networks and natural language processing. FANG Jinyun, Ph.D., professor. His research interests include massive spatial information processing technologies.
Service
E-mail this article
Add to my bookshelf
Add to citation manager
E-mail Alert
RSS
Articles by authors
CHEN Juan
ZHAO Xinchao
SUI Jingyan
QI Lin
TIAN Chen
PANG Liang
FANG Jinyun
Cite this article:   
CHEN Juan,ZHAO Xinchao,SUI Jingyan等. Narrative-Driven Large Language Model for Temporal Knowledge Graph Prediction[J]. Pattern Recognition and Artificial Intelligence, 2024, 37(8): 715-728.
URL:  
http://manu46.magtech.com.cn/Jweb_prai/EN/10.16451/j.cnki.issn1003-6059.202408005      OR     http://manu46.magtech.com.cn/Jweb_prai/EN/Y2024/V37/I8/715
Copyright © 2010 Editorial Office of Pattern Recognition and Artificial Intelligence
Address: No.350 Shushanhu Road, Hefei, Anhui Province, P.R. China Tel: 0551-65591176 Fax:0551-65591176 Email: bjb@iim.ac.cn
Supported by Beijing Magtech  Email:support@magtech.com.cn