Deep Learning for Joint Source-Channel Coding of Text

By Nariman Farsad, Milind Rao, Andrea J. Goldsmith. 2018

463 citations recorded by the source corpus.

We consider the problem of joint source and channel coding of structured data such as natural language over a noisy channel. The typical approach to this problem in both theory and practice involves performing source coding to first compress the text and then channel coding to add robustness for the transmission across the channel. This approach is optimal in terms of minimizing end-to-end distortion with arbitrarily large block lengths of both the source and channel codes when transmission is over discrete memoryless channels. However, the optimality of this approach is no longer ensured for documents of finite length and limitations on the length of the encoding. We will show in this scenario that we can achieve lower word error rates by developing a deep learning based encoder and decoder. While the approach of separate source and channel coding would minimize bit error rates, our approach preserves semantic information of sentences by first embedding sentences in a semantic space where sentences closer in meaning are located closer together, and then performing joint source and channel coding on these em-beddings.

Subfields: Artificial Intelligence, Computer Vision and Pattern Recognition, Molecular Biology

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

In Computer Vision and Pattern Recognition

In Molecular Biology

Citations in the corpus

Wireless Network Intelligence at the Edge (2018, background): “” For instance, this is viable by improving spectral efficiency (SE) via enabling real-time joint source–channel coding [42], channel-agnostic E2E communications [19], and interference management [43].”
Learning Task-Oriented Communication for Edge Inference: An Information Bottleneck Approach (2021, methodology): “JSCC has also been applied to natural language processing for text transmission, which was accomplished by incorporating the semantic information of sentences using recurrent neural networks [22].”
Semantic Communications for Future Internet: Fundamentals, Applications, and Challenges (2022, unknown): “2) SE for text data: Inspired by the success of DL in NLP such as machine translation, the authors in [70] pioneer the implementation of SemCom for text transmission.”
Deep Learning-Based End-to-End Wireless Communication Systems With Conditional GANs as Unknown Channels (2019, methodology): “In addition, deep learning based methods have also shown impressive improvement by jointly optimizing the conventional communication blocks, including joint channel estimation and detection [12], joint channel encoding and source encoding [13].”
A Tutorial on Ultrareliable and Low-Latency Communications in 6G: Integrating Domain Knowledge Into Deep Learning (2021, methodology): “The encoder and the decoder of the communication system can be approximated by two DNNs [61], [228].”
A Lite Distributed Semantic Communication System for Internet of Things (2020, methodology): “[21] designed joint source-channel coding for erasure channel by using a recurrent neural network (RNN) and a fully-connected neural network (FCN), where the system”
Nonlinear Transform Source-Channel Coding for Semantic Communications (2021, background): “As one modern version, recent deep learning methods for realizing JSCC have stimulated signiﬁcant interest in both AI and wireless communication communities [7]–[13].”
Channel Agnostic End-to-End Learning Based Communication Systems with Conditional GAN (2018, methodology): “In addition, deep learning based methods also show potential improvement by jointly optimizing the processing blocks, including joint channel estimation and detection [6], joint channel encoding and source encoding [7].”
Deep Learning in Physical Layer Communications (2018, methodology): “A joint source-channel coding based on DL has been proposed in [11].”
DeepJSCC-f: Deep Joint Source-Channel Coding of Images With Feedback (2019, background): “While [39] focuses on text as the information source and binary channels, and [40] deals with lossy data storage, image”
Task-Oriented Multi-User Semantic Communications (2021, background): “[8] designed the initial deep joint source-channel coding for text transmission, in which the text sentences are encoded into fixed-length bit streams over simple channel environments.”
Semantic Communications: Principles and Challenges (2021, methodology): “For erasure channels, Farsad et al. [10] developed a long short-term memory (LSTM) enabled JSCC for text transmission.”
Wireless Image Transmission Using Deep Source Channel Coding With Attention Modules (2020, background): “For example, [28] has proposed DL based JSCC for the transmission of text over wireless communications channels for the first time.”