Deep Learning-Enabled Text Semantic Communication under Interference: An Empirical Study

At the confluence of 6G, deep learning (DL), and natural language processing (NLP), DL-enabled text semantic communication (SemCom) has emerged as a 6G enabler since it minimizes bandwidth consumption, transmission delay, and power usage. Among existing text SemCom techniques, a popular text SemCom scheme -- that can reliably transmit semantic information in the low signal-to-noise ratio (SNR) regimes -- is DeepSC, whose fundamental asymptotic performance limits under radio frequency interference (RFI) were accurately predicted by our recently developed theory [1]. Although our theory was corroborated by simulations, trained deep networks can defy classical statistical wisdom, calling for extensive computer experiments. This empirical work thus follows using the training, validation, and testing sets tokenized and vectorized from the Proceedings of the European Parliament (Europarl) dataset. Specifically, we train the DeepSC architecture in Keras 2.9 with TensorFlow 2.9 as a backend and test it under Gaussian multi-interferer RFI received over Rayleigh fading channels. Our testing results corroborate that DeepSC produces semantically irrelevant sentences under huge Gaussian RFI emitters, validating our theory. Therefore, a fundamental 6G design paradigm for interference-resistant and robust SemCom (IR$^2$ SemCom) is needed.