Extended context-based semantic communication system for text transmission

作     者：Yueling Liu Shengteng Jiang Yichi Zhang Kuo Cao Li Zhou Boon-Chong Seet Haitao Zhao Jibo Wei Yueling Liu;Shengteng Jiang;Yichi Zhang;Kuo Cao;Li Zhou;Boon-Chong Seet;Haitao Zhao;Jibo Wei

作者机构：College of Electronic Science and TechnologyNational University of Defense TechnologyChangsha410073China Department of Electrical and Electronic EngineeringAuckland University of TechnologyAucklandNew Zealand 

出 版 物：《Digital Communications and Networks》 (数字通信与网络（英文版）)

年 卷 期：2024年第10卷第3期

页      面：568-576页

核心收录：

学科分类：0810[工学-信息与通信工程] 08[工学] 081001[工学-通信与信息系统] 

基　　金：supported in part by the National Natural Science Foundation of China under Grant No.61931020,U19B2024,62171449,,62001483 in part by the science and technology innovation Program of Hunan Province under Grant No.2021JJ40690 

主　　题：semantic communication extended context Transformer-XL 

摘      要：Context information is significant for semantic extraction and recovery of messages in semantic ***,context information is not fully utilized in the existing semantic communication systems since re-lationships between sentences are often *** this paper,we propose an Extended Context-based Semantic Communication(ECSC)system for text transmission,in which context information within and between sentences is explored for semantic representation and *** the encoder,self-attention and segment-level relative attention are used to extract context information within and between sentences,*** addition,a gate mechanism is adopted at the encoder to incorporate the context information from different *** the decoder,Transformer-XL is introduced to obtain more semantic information from the historical communication processes for semantic *** results show the effectiveness of our proposed model in improving the semantic accuracy between transmitted and recovered messages under various channel conditions.