Knowledge-Aware Semantic Communication System Design

TL;DR

This paper proposes a knowledge-aware semantic communication system for 6G that transmits only relevant semantic data using auto-encoders, improving efficiency and accuracy compared to existing methods.

Contribution

It introduces a novel semantic communication framework utilizing shared knowledge bases and auto-encoders to efficiently transmit and recover semantic data.

Findings

The semantic distortion function has a proven upper bound.

The proposed system outperforms state-of-the-art in words per sentence.

Numerical results show improved accuracy of reconstructed sentences.

Abstract

The recent emergence of 6G raises the challenge of increasing the transmission data rate even further in order to break the barrier set by the Shannon limit. Traditional communication methods fall short of the 6G goals, paving the way for Semantic Communication (SemCom) systems. These systems find applications in wide range of fields such as economics, metaverse, autonomous transportation systems, healthcare, smart factories, etc. In SemCom systems, only the relevant information from the data, known as semantic data, is extracted to eliminate unwanted overheads in the raw data and then transmitted after encoding. In this paper, we first use the shared knowledge base to extract the keywords from the dataset. Then, we design an auto-encoder and auto-decoder that only transmit these keywords and, respectively, recover the data using the received keywords and the shared knowledge. We show analytically that the overall semantic distortion function has an upper bound, which is shown in the literature to converge. We numerically compute the accuracy of the reconstructed sentences at the receiver. Using simulations, we show that the proposed methods outperform a state-of-the-art method in terms of the average number of words per sentence.