Recently, task-oriented semantic communication has received increasing attention due to its potential to transform the communication landscape by going beyond the Shannon paradigm. While most existing researches focus on a single task, we propose a multi-task semantic communication system for text tasks, inspired by the impressive results of multitask learning and bidirectional encoder representations from transformers (BERT). Based on BERT, the proposed system extracts semantic information from the text at the transmitter and then transmits it to the receiver, which aims to accomplish a series of different tasks. The transmitter and receiver would be trained jointly in an end-to-end manner. Compared with the traditional communication system, the proposed model is more robust to distortion caused by physical channels and exhibits better performance, especially in the low signal-to-noise ratio regime. Moreover, we investigate the relationship between the number of tasks and the required length of transmitted symbols in a multi-task setting.


    Zugriff

    Zugriff prüfen

    Verfügbarkeit in meiner Bibliothek prüfen

    Bestellung bei Subito €


    Exportieren, teilen und zitieren



    Titel :

    A Multi-Task Semantic Communication System for Natural Language Processing


    Beteiligte:
    Sheng, Yucheng (Autor:in) / Li, Fang (Autor:in) / Liang, Le (Autor:in) / Jin, Shi (Autor:in)


    Erscheinungsdatum :

    01.09.2022


    Format / Umfang :

    897947 byte





    Medientyp :

    Aufsatz (Konferenz)


    Format :

    Elektronische Ressource


    Sprache :

    Englisch



    Semantic Communication Approach for Multi-Task Image Transmission

    Zhang, Zhenguo / Yang, Qianqian / He, Shibo et al. | IEEE | 2022


    Universal Weighted-Knowledge Bases for Task-Unaware Semantic Communication Systems

    Jiang, Shiyao / Jiao, Jian / Zhang, Ke et al. | IEEE | 2024


    UAV Path Planning in Multi-Task Environments with Risks through Natural Language Understanding

    Chang Wang / Zhiwei Zhong / Xiaojia Xiang et al. | DOAJ | 2023

    Freier Zugriff

    Analysis of Controller-Pilot Communication Messages with Natural Language Processing

    Rakas, Jasenka / Alvarado, Matthew / He, Kezhi et al. | TIBKAT | 2022


    Analysis of Controller-Pilot Communication Messages with Natural Language Processing

    Rakas, Jasenka / Alvarado, Matthew / He, Kezhi et al. | AIAA | 2022