English

Semantic Importance-Aware Communications Using Pre-trained Language Models

Signal Processing 2023-07-10 v2

Abstract

This letter proposes a semantic importance-aware communication (SIAC) scheme using pre-trained language models (e.g., ChatGPT, BERT, etc.). Specifically, we propose a cross-layer design with a pre-trained language model embedded in/connected by the cross-layer manager. The pre-trained language model is utilized to quantify the semantic importance of data frames. Based on the quantified semantic importance, we investigate semantic importance-aware power allocation. Unlike existing deep joint source-channel coding (Deep-JSCC)-based semantic communication schemes, SIAC can be directly embedded into current communication systems by only introducing a cross-layer manager. Our experimental results show that the proposed SIAC scheme can achieve lower semantic loss than existing equal-priority communications.

Keywords

Cite

@article{arxiv.2302.07142,
  title  = {Semantic Importance-Aware Communications Using Pre-trained Language Models},
  author = {Shuaishuai Guo and Yanhu Wang and Shujing Li and Nasir Saeed},
  journal= {arXiv preprint arXiv:2302.07142},
  year   = {2023}
}

Comments

Accepted by IEEE Communications Letters, Semantic communications, pre-trained language model, ChatGPT, BERT, data importance

R2 v1 2026-06-28T08:39:57.991Z