A Large Language Model Driven Knowledge Graph Construction Scheme for Semantic Communication
Source abstract
Abstract
This study presents a knowledge graph construction scheme leveraging large language models (LLMs) for task-oriented semantic communication systems. The proposed methodology systematically addresses four critical stages: corpus collection, entity extraction and relationship analysis, knowledge base generation, and dynamic updating mechanisms. It is worth noting that prompt engineering is combined with few-shot learning to enhance reliability and accuracy in this methodology. Experimental demonstration showed that this methodology had superior entity extraction performance, achieving 89.7% precision and 92.3% recall rate. This scheme overcomes the demand for domain knowledge and the labor cost of traditional knowledge base construction schemes. It greatly improves the construction efficiency of knowledge graphs. This paper provides an efficient and reliable task knowledge base construction scheme for task-oriented semantic communication, which is expected to promote its wider application.
Source: crossref · Quality: baseline
Research context
OpenAlex topics: Advanced Graph Neural Networks · Semantic Web and Ontologies · Cognitive Computing and Networks
SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.
Affiliations
College of Information and Communication, National University of Defense Technology, Wuhan 430030, China
Funding
National Natural Science Foundation of China · National University of Defense Technology
References (22)
Show source-provided references
1. The Mathematical Theory of Communication
2. Jiang, S., Liu, Y., Zhang, Y., Luo, P., Cao, K., Xiong, J., Zhao, H., and Wei, J. (2022). Reliable Semantic Communication System Enabled by Knowledge Graph. Entropy, 24.10.3390/e24060846 ↗
3. Liang, J., Xiao, Y., Li, Y., Shi, G., and Bennis, M. (2022, January 16). Life-Long Learning for Reasoning-Based Semantic Communication. Proceedings of the 2022 IEEE International Conference on Communications Workshops (ICC Workshops), Seoul, Republic of Korea.10.1109/ICCWorkshops53468.2022.9814575 ↗
4. Xiao, Y., Li, Y., Shi, G., and Poor, H.V. (2022, January 16). Reasoning on the Air: An Implicit Semantic Communication Architecture. Proceedings of the 2022 IEEE International Conference on Communications Workshops (ICC Workshops), Seoul, Republic of Korea.10.1109/ICCWorkshops53468.2022.9814604 ↗
5. Cross-Modal Semantic Communications10.1109/MWC.008.2200180 ↗
6. An Automatic Literature Knowledge Graph and Reasoning Network Modeling Framework Based on Ontology and Natural Language Processing10.1016/j.aei.2019.100959 ↗
7. GPT-3: Its Nature, Scope, Limits, and Consequences10.1007/s11023-020-09548-1 ↗
8. Kommineni, V.K., König-Ries, B., and Samuel, S. (2024). From Human Experts to Machines: An LLM Supported Approach to Ontology and Knowledge Graph Construction. arXiv.
9. Zhang, Y., and Hao, Y. (2024). Traditional Chinese Medicine Knowledge Graph Construction Based on Large Language Models. Electronics, 13.10.3390/electronics13071395 ↗
10. Shi, G., Gao, D., Song, X., Chai, J., Yang, M., Xie, X., Li, L., and Li, X. (2021). A New Communication Paradigm: From Bit Accuracy to Semantic Fidelity. arXiv.
11. Cognitive Semantic Communication Systems Driven by Knowledge Graph: Principle, Implementation, and Performance Evaluation10.1109/TCOMM.2023.3318605 ↗
12. Semantic Communications With Artificial Intelligence Tasks: Reducing Bandwidth Requirements and Improving Artificial Intelligence Task Performance10.1109/MIE.2022.3174331 ↗
13. Hu, Q., Zhang, G., Qin, Z., Cai, Y., Yu, G., and Li, G.Y. (2022, January 26–29). Robust Semantic Communications Against Semantic Noise. Proceedings of the 2022 IEEE 96th Vehicular Technology Conference (VTC2022-Fall), London, UK.10.1109/VTC2022-Fall57202.2022.10012843 ↗
14. Semantic Importance-Aware Communications Using Pre-Trained Language Models10.1109/LCOMM.2023.3293805 ↗
15. Large AI Model-Based Semantic Communications10.1109/MWC.001.2300346 ↗
16. Guo, C., Xi, J., He, Z., Liu, J., and Yang, J. (2024). A Knowledge Base Driven Task-Oriented Image Semantic Communication Scheme. Remote Sens., 16.10.3390/rs16214044 ↗
17. Guo, S., Wang, Y., and Zhangz, P. (2022, January 26–29). Signal Shaping for Semantic Communication Systems with A Few Message Candidates. Proceedings of the 2022 IEEE 96th Vehicular Technology Conference (VTC2022-Fall), London, UK.10.1109/VTC2022-Fall57202.2022.10012981 ↗
18. Large AI Model Empowered Multimodal Semantic Communications10.1109/MCOM.001.2300575 ↗
19. Nam, H., Park, J., Choi, J., Bennis, M., and Kim, S.-L. (2024, January 14–19). Language-Oriented Communication with Semantic Coding and Knowledge Distillation for Text-to-Image Generation. Proceedings of the ICASSP 2024–2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), Seoul, Republic of Korea.10.1109/ICASSP48485.2024.10446638 ↗
20. Zhang, Y., Li, Y., Cui, L., Cai, D., Liu, L., Fu, T., Huang, X., Zhao, E., Zhang, Y., and Chen, Y. (2023). Siren’s Song in the AI Ocean: A Survey on Hallucination in Large Language Models. arXiv.
21. Ni, X., Li, P., and Li, H. (2023). Unified Text Structuralization with Instruction-Tuned Language Models. arXiv.
22. Improving Large Language Models for Clinical Named Entity Recognition via Prompt Engineering10.1093/jamia/ocad259 ↗