摘要
Semantic communication has emerged as a promising paradigm to overcome Shannon's transmission limits. Existing research has primarily focused on deep neural network (DNN) solutions to realize semantic communication. However, these approaches often suffer from inherent limitations in terms of interpretability and transparency in feature extraction. To address this challenge, we propose a relation-aware Knowledge Graph Bidirectional Encoder Representations from Transformers (KG-BERT) semantic communication system, which combines two complementary approaches: the structured representation of entity relationships in knowledge graphs and BERT's ability to understand natural language context. This integration enables our system to maintain semantic meaning even in noisy channels while providing transparent reasoning processes. Furthermore, we enhance the system with two key innovations: (1) a relation-aware strategy that significantly improves transmission privacy and reduces bandwidth, and (2) an entity correction algorithm that enables robust entity recovery. Experimental results demonstrate that our KG-BERT semantic communication system significantly outperforms state-of-the-art (SOTA) KG-based and DNN-based semantic communication baselines, achieving sentence similarity scores that are 78 percentage higher in the Additive White Gaussian Noise (AWGN) channel and 55 percentage higher in the Rayleigh fading channel at signal-to-noise ratio (SNR) of -5dB, demonstrating particular advantages in low SNR environments. © 2025 IEEE.