RECORD
Semantic Communication with Memory
Signal Processing · Submitted 22 Mar 2023
abstract compiled · 2026-09-23 · no language-model review
The authors' main claim Numerical results show that the proposed Mem-DeepSC is superior to benchmarks in terms of answer accuracy and transmission efficiency, i.e., number of transmitted symbols.
The compiled record
The paper's own sentences, arranged. Each label is drawn from a closed vocabulary; the number beside it is the probability the classifier gave that label. Numbers in the tables are the authors', checked by code. No sentence in this record was written by a model.
Open the compiled record
The abstract, sentence by sentence
While semantic communication succeeds in efficiently transmitting due to the strong capability to extract the essential semantic information, it is still far from the intelligent or human-like communications. In this paper, we introduce an essential component, memory, into semantic communications to mimic human communications. Particularly, we investigate a deep learning (DL) based semantic communication system with memory, named Mem-DeepSC, by considering the scenario question answer task. We exploit the universal Transformer based transceiver to extract the semantic information and introduce the memory module to process the context information. Moreover, we derive the relationship between the length of semantic signal and the channel noise to validate the possibility of dynamic transmission. Specially, we propose two dynamic transmission methods to enhance the transmission reliability as well as to reduce the communication overhead by masking some unessential elements, which are recognized through training the model with mutual information. Numerical results show that the proposed Mem-DeepSC is superior to benchmarks in terms of answer accuracy and transmission efficiency, i.e., number of transmitted symbols.
background contribution method result interpretation main claim
| # | sentence | role | the authors' own work | states the main conclusion | strength |
|---|---|---|---|---|---|
| s0 | While semantic communication succeeds in efficiently transmitting due to the strong capability to extract the essential semantic information, it is still far from the intelligent or human-like communications. | background 0.62 | 0.08 | 0.03 | asserted 1.00 |
| s1 | In this paper, we introduce an essential component, memory, into semantic communications to mimic human communications. | contribution 0.99 | 0.88 | 0.06 | asserted 0.96 |
| s2 | Particularly, we investigate a deep learning (DL) based semantic communication system with memory, named Mem-DeepSC, by considering the scenario question answer task. | contribution 0.86 | 0.92 | 0.04 | asserted 0.98 |
| s3 | We exploit the universal Transformer based transceiver to extract the semantic information and introduce the memory module to process the context information. | method 0.99 | 0.92 | 0.03 | asserted 0.99 |
| s4 | Moreover, we derive the relationship between the length of semantic signal and the channel noise to validate the possibility of dynamic transmission. | contribution 0.63 | 0.94 | 0.03 | asserted 0.79 |
| s5 | Specially, we propose two dynamic transmission methods to enhance the transmission reliability as well as to reduce the communication overhead by masking some unessential elements, which are recognized through training the model with mutual information. | method 0.73 | 0.95 | 0.09 | asserted 1.00 |
| s6 | Numerical results show that the proposed Mem-DeepSC is superior to benchmarks in terms of answer accuracy and transmission efficiency, i.e., number of transmitted symbols. | result 1.00 | 0.96 | 0.85 | asserted 1.00 |
What was examined, and what was not
- arXiv listing abstract v1
- full text
- figures and tables
- references and citing sentences
- relations to other papers
- P abstract
- S sections
- T body sentences
- C citations
- R cross-paper relations
The paper
Original abstract
While semantic communication succeeds in efficiently transmitting due to the strong capability to extract the essential semantic information, it is still far from the intelligent or human-like communications. In this paper, we introduce an essential component, memory, into semantic communications to mimic human communications. Particularly, we investigate a deep learning (DL) based semantic communication system with memory, named Mem-DeepSC, by considering the scenario question answer task. We exploit the universal Transformer based transceiver to extract the semantic information and introduce the memory module to process the context information. Moreover, we derive the relationship between the length of semantic signal and the channel noise to validate the possibility of dynamic transmission. Specially, we propose two dynamic transmission methods to enhance the transmission reliability as well as to reduce the communication overhead by masking some unessential elements, which are recognized through training the model with mutual information. Numerical results show that the proposed Mem-DeepSC is superior to benchmarks in terms of answer accuracy and transmission efficiency, i.e., number of transmitted symbols.
Human review
How the literature uses it
1 arXiv paper cite this in 2 sentences
Papers citing it
Cites it as background 1 paper
-
With the development of deep learning (DL) techniques, many DL-enabled semantic communication systems have been proposed recently [ref] .
FAST: Feature Arrangement for Semantic Transmission · Introduction · 1.00
What it cites · 2 sentences without a confident label
Compares with 1 paper
-
Different from [ref] , the authors have designed the video semantic communication by converting the video to text at the transmitter and recovering the video from the text at the receiver.
Wireless Semantic Communications for Video Conferencing · Introduction · 0.94
Cites as background 7 papers
-
To materialize the vision, semantic communication [ref] is a communication paradigm by directly delivering the meanings of information, and extracting and transmitting only important information relevant to the task at the receiver.
Semantic Communications: Principles and Challenges · Introduction · 0.95
-
Huang et al. [ref] have designed the image semantic coding method by introducing the framework of rate-distortion, which can save the number of bits as well as keep the good quality of the reconstructed image.
Towards Semantic Communications: Deep Learning-Based Image Semantic Coding · Introduction · 0.88
-
Jiang et al. [ref] have investigated the application of semantic communications in the video conference, in which the proposed system can maintain high resolution by transmitting some keypoints to represent motions and keep the low communication overheads.
Wireless Semantic Communications for Video Conferencing · Introduction · 0.99
Discussion
Know something about this paper? Leave a comment, or highlight any passage above to comment on it.