高效融合全局和局部上下文特征的语义通信系统

doi:10.11959/j.issn.1000-436x.2023133

Abstract

Abstract:

A communication system based on extended contextual semantic features was proposed by using an end-to-end integrated design method based on deep learning.Unlike existing research that focused only on local context while neglecting global context, the proposed system integrated both local and global contextual knowledge, semantic encoding and decoding was utilized by extended contextual knowledge, thereby enhancing the reliability of the semantic communication system.At the transmitter, efficient semantic representation was achieved through extended contextual semantic encoding.At the receiver, the accuracy of semantic inference was improved by combining mechanisms such as historical communication text mining, contextual semantic feature learning, and heuristic graph-based decoding strategy.When comparing with the traditional communication system and the existing semantic communication systems, simulation results demonstrate that the proposed system significantly improves the reliability of the communication system under low signal-to-noise ratio.

Key words: semantic communication, local context, global context, extended context, historical communication text

CLC Number:

TN929.5

Peng LUO, Yueling LIU, Yuyuan ZHANG, Kuo CAO, Haitao ZHAO, Jibo WEI. Semantic communication system with efficient integration of global and local context features[J]. Journal on Communications, 2023, 44(7): 14-25.

Figures/Tables 15

References 32

[1]	SHANNON C E . A mathematical theory of communication[J]. Bell System Technical Journal, 1948,27(4): 623-656.
[2]	WARREN W . Recent contributions to the mathematical theory of communication[J]. ETC:A Review of General Semantics, 2017,74(1/2): 136-157.
[3]	STRINATI E C , BARBAROSSA S , GONZALEZ-JIMENEZ J L , ,et al. 6G:the next frontier:from holographic messaging to artificial intelligence using subterahertz and visible light communication[J]. IEEE Vehicular Technology Magazine, 2019,14(3): 42-50.
[4]	张海君, 陈安琪, 李亚博 ,等. 6G移动网络关键技术[J]. 通信学报, 2022,43(7): 189-202.
	ZHANG H J , CHEN A Q , LI Y B ,et al. Key technologies of 6G mobile network[J]. Journal on Communications, 2022,43(7): 189-202.
[5]	OUYANG L , WU J , JIANG X ,et al. Training language models to follow instructions with human feedback[J]. arXiv Preprint,arXiv:2203.02155, 2022.
[6]	XIE H Q , QIN Z J , LI G Y ,et al. Deep learning enabled semantic communication systems[J]. IEEE Transactions on Signal Processing, 2021,69: 2663-2675.
[7]	XIE H Q , QIN Z J . A lite distributed semantic communication system for Internet of things[J]. IEEE Journal on Selected Areas in Communications, 2021,39(1): 142-153.
[8]	SANA M , STRINATI E C . Learning semantics:an opportunity for effective 6G communications[C]// Proceedings of 2022 IEEE 19th Annual Consumer Communications ＆ Networking Conference (CCNC). Piscataway:IEEE Press, 2022: 631-636.
[9]	ZHOU Q Y , LI R P , ZHAO Z F ,et al. Semantic communication with adaptive universal transformer[J]. IEEE Wireless Communications Letters, 2022,11(3): 453-457.
[10]	LU K , ZHOU Q Y , LI R P ,et al. Rethinking modern communication from semantic coding to semantic communication[J]. IEEE Wireless Communications, 2023,30(1): 158-164.
[11]	JIANG P W , WEN C K , JIN S ,et al. Deep source-channel coding for sentence semantic transmission with HARQ[J]. IEEE Transactions on Communications, 2022,70(8): 5225-5240.
[12]	FARSAD N , RAO M , GOLDSMITH A . Deep learning for joint source-channel coding of text[C]// Proceedings of 2018 IEEE International Conference on Acoustics,Speech and Signal Processing (ICASSP). Piscataway:IEEE Press, 2018: 2326-2330.
[13]	RAO M , FARSAD N , GOLDSMITH A . Variable length joint source-channel coding of text using deep neural networks[C]// Proceedings of 2018 IEEE 19th International Workshop on Signal Processing Advances in Wireless Communications (SPAWC). Piscataway:IEEE Press, 2018: 1-5.
[14]	ZHANG Y C , ZHAO H T , WEI J B ,et al. Context-based semantic communication via dynamic programming[J]. IEEE Transactions on Cognitive Communications and Networking, 2022,8(3): 1453-1467.
[15]	BAR-HAIM R , DAGAN I , GREENTAL I ,et al. Semantic inference at the lexical-syntactic level for textual entailment recognition[C]// Proceedings of the ACL-PASCAL Workshop on Textual Entailment and Paraphrasing. Stroudsburg:ACL Press, 2007: 131-136.
[16]	LIU Y , SUN C , LIN L ,et al. Learning natural language inference using bidirectional LSTM model and inner-attention[J]. arXiv Preprint,arXiv:1605.09090, 2016.
[17]	PARIKH A , T?CKSTR?M O , DAS D , et al . A decomposable attention model for natural language inference[C]// Proceedings of the 2016 Conference on Empirical Methods in Natural Language Processing. Stroudsburg:ACL Press, 2016: 2249-2255.
[18]	ZHANG K , CHEN E H , LIU Q ,et al. A context-enriched neural network method for recognizing lexical entailment[C]// Proceedings of the AAAI Conference on Artificial Intelligence. Palo Alto:AAAI Press, 2017: 3127-3133.
[19]	TURNEY P D , MOHAMMAD S M . Experiments with three approaches to recognizing lexical entailment[J]. Natural Language Engineering, 2015,21(3): 437-476.
[20]	张亦弛, 张平, 魏急波 ,等. 面向智能体的语义通信:架构与范例[J]. 中国科学(信息科学), 2022,52(5): 907-921.
	ZHANG Y C , ZHANG P , WEI J B ,et al. Semantic communication for intelligent devices:architectures and a paradigm[J]. Scientia Sinica (Informationis), 2022,52(5): 907-921.
[21]	ZHENG Z X , YUE X , HUANG S J ,et al. Towards making the most of context in neural machine translation[C]// Proceedings of the Twenty-Ninth International Joint Conference on Artificial Intelligence. California:International Joint Conferences on Artificial Intelligence Organization, 2020: 3983-3989.
[22]	LIU Y L , JIANG S T , ZHANG Y C ,et al. Extended context-based semantic communication system for text transmission[J]. Digital Communications and Networks, 2022,10: 1-11.
[23]	DEVLIN J , CHANG M W , LEE K ,et al. BERT:pre-training of deep bidirectional transformers for language understanding[C]// Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics:Human Language Technologies (NAACL). New York:ACM Press, 2019: 4171-4186.
[24]	VASWANI A , SHAZEER N , PARMAR N ,et al. Attention is all you need[C]// Proceedings of the 31st International Conference on Neural Information Processing Systems. New York:ACM Press, 2017: 6000-6010.
[25]	DAI Z H , YANG Z L , YANG Y M ,et al. Transformer-XL:attentive language models beyond a fixed-length context[C]// Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics. Stroudsburg:ACL Press, 2019: 2978-2988.
[26]	FREITAG M , AL-ONAIZAN Y . Beam search strategies for neural machine translation[J]. arXiv Preprint,arXiv:1702.01806, 2017.
[27]	KOEHN P . Europarl:a parallel corpus for statistical machine translation[C]// Proceedings of Machine Translation Summit X:Papers.[S.l.:s.n.], 2005: 79-86.
[28]	JUBA B , SUDAN M . Universal semantic communication I[C]// Proceedings of the Fortieth Annual ACM Symposium on Theory of Computing. New York:ACM Press, 2008: 123-132.
[29]	PAPINENI K , ROUKOS S , WARD T ,et al. BLEU:a method for automatic evaluation of machine translation[C]// Proceedings of the 40th Annual Meeting on Association for Computational Linguistics. Morristown:Association for Computational Linguistics, 2001: 311-318.
[30]	BANERJEE S , LAVIE A . METEOR:an automatic metric for MT evaluation with improved correlation with human judgments[C]// Proceedings of the ACL Workshop on Intrinsic and Extrinsic Evaluation Measures for Machine Translation and/or Summarization. Stroudsburg:ACL Press, 2005: 65-72.
[31]	MILLER G A . WordNet[J]. Communications of the ACM, 1995,38(11): 39-41.
[32]	MICROSOF T . Neural network intelligence (version 2.0)[R]. 2021.

Metrics

Recommended 0

No Suggested Reading articles found!

系统模块	神经网络层名	维度	激活函数
语义编码器	3个局部上下文编码层和	128维	Linear
	一个全局上下文编码层	256维	Linear
信道编码器	Reshape层	128维	Linear
	3个Dense层	16维	Linear
信道	AWGN/Rayleigh	无	无
信道译码器	Reshape层	256维	Linear
	2个Dense层	128维	Linear
语义译码器	3个扩展上下文译码层	128维	ReLU
	上下文语义特征学习层	768维	无
	（训练阶段）
	线性层	128维	Linear
	预测概率层	同词库维	Softmax
		度一致
	候选概率层	无	无

不同算法	解译文本直观输出	错误单词数目
发送句子	do you think it would be possible to draw up a voluntary agreement , in conjunction with the economics and finance council , with a view to agreeing a form of words covering both auctions and beauty contests , and then in future , spend a certain amount of the proceeds on the e commerce sector	—
Huffman + CC	do you thtpu it would rgatdaodtls oe draw up a fral ntary agreement , in cfnsmf ctitn with t nseconomics ansnfinance coh neeg , seati a vtoveo bteeerll a dssr ef woersalshas	46
DeepSC×5	madam president,think it be with possible to draw up a voluntary union,in conjunction of trade,or and	30
	energy on with a certain legal funds,thank it explain words market,both few more the states and then in i spend not amount spoke against the final on the years in sector
Extend Context-SC	it is i think that i would be possible to draw up a voluntary area,and the economics and finance council,	15
	with the view that agreeing a form of words of both auctions and animal incineration, and then occurred a certain amount of the formation of the e commerce sector
所提算法上下文知识学习	do you think it would be possible to draw up a voluntary agreement,in conjunction with the catchesand finance I would agree with a view to agreeing to words covering both the auctions and exaggerated and will then,and in future,spend a certain amount of the proceeds on the e commerce sector	9
所提算法上下文知识学习（集束搜索）	do you think it would be possible to draw up a voluntary agreement,in conjunction with the catches and finance council,with the view to agreeing a form of words covering both auctions and exaggerated and will then,and in future,spend a certain amount of the initiatives in the e commerce sector	6

不同算法	网络参数量/个	FLOP
DeepSC×3	5.005×10 ⁶	4.968×10 ⁶
DeepSC×5	5.928×10 ⁶	5.886×10 ⁶
Extend Context-SC	5.255×10 ⁶	5.247 ×10 ⁶
所提算法（集束搜索）	5.739×10 ⁶	5.732×10 ⁶

Semantic communication system with efficient integration of global and local context features

RichHTML

PDF

Knowledge

Abstract

Cite this article

share this article

Figures/Tables 15

References 32

Related Articles 9

Metrics

Recommended 0

[1]	Rongpeng LI, Bingyan WANG, Honggang ZHANG, Zhifeng ZHAO. Design of knowledge enhanced semantic communication receiver [J]. Journal on Communications, 2023, 44(6): 70-76.
[2]	Zhijin QIN, Tantan ZHAO, Fan LI, Xiaoming TAO. Survey of research on multimodal semantic communication [J]. Journal on Communications, 2023, 44(5): 28-41.
[3]	Guangming SHI, Minxi YANG, Dahua GAO, Jingxuan CHAI. Communication framework for directed transmission of informative semantic [J]. Journal on Communications, 2023, 44(5): 15-27.
[4]	Ping ZHANG, Kai NIU, Shengshi YAO, Jincheng DAI. Semantic communications for future: basic principle and implementation methodology [J]. Journal on Communications, 2023, 44(5): 1-14.
[5]	Ping ZHANG, Jincheng DAI, Yuming ZHANG, Sixian WANG, Xiaoqi QIN, Kai NIU. Nonlinear transform coding for semantic communications [J]. Journal on Communications, 2023, 44(4): 1-14.
[6]	Feibo JIANG, Yubo PENG, Li DONG. Deep image semantic communication model for 6G [J]. Journal on Communications, 2023, 44(3): 198-208.
[7]	Haijun ZHANG, Anqi CHEN, Yabo LI, Keping LONG. Key technologies of 6G mobile network [J]. Journal on Communications, 2022, 43(7): 189-202.
[8]	Chuanhong LIU, Caili GUO, Yang YANG, Jiujiu CHEN, Meiyi ZHU, Lu’nan SUN. Intelligent task-oriented semantic communications:theory, technology and challenges [J]. Journal on Communications, 2022, 43(6): 41-57.
[9]	Chuanhong LIU, Caili GUO, Yang YANG, Chunyan FENG, Qizheng SUN, Jiujiu CHEN. Intelligent task-oriented semantic communication method in artificial intelligence of things [J]. Journal on Communications, 2021, 42(11): 97-108.