Semantic Forwarding for Next Generation Relay Networks

We consider cooperative semantic text communications facilitated by a relaynode. We propose two types of semantic forwarding: semantic lossy forwarding(SLF) and semantic predict-and-forward (SPF). Both are machine learning aidedapproaches, and, in particular, utilize attention mechanisms at the relay toestablish a dynamic semantic state, updated upon receiving a new source signal.In the SLF model, the semantic state is used to decode the received sourcesignal; whereas in the SPF model, it is used to predict the next source signal,enabling proactive forwarding. Our proposed forwarding schemes do not need anychannel state information and exhibit consistent performance regardless of therelay's position. Our results demonstrate that the proposed semantic forwardingtechniques outperform conventional semantic-agnostic baselines.