Semantic Communication with Adaptive Universal Transformer
This work addresses semantic communication for NLP applications, but it appears incremental as it builds on existing transformer methods with a specific adaptation.
The paper tackles the problem of semantic communication over noisy channels by proposing a new system based on Universal Transformer with an adaptive circulation mechanism, achieving better end-to-end performance under various channel conditions.
With the development of deep learning (DL), natural language processing (NLP) makes it possible for us to analyze and understand a large amount of language texts. Accordingly, we can achieve a semantic communication in terms of joint semantic source and channel coding over a noisy channel with the help of NLP. However, the existing method to realize this goal is to use a fixed transformer of NLP while ignoring the difference of semantic information contained in each sentence. To solve this problem, we propose a new semantic communication system based on Universal Transformer. Compared with the traditional transformer, an adaptive circulation mechanism is introduced in the Universal Transformer. Through the introduction of the circulation mechanism, the new semantic communication system can be more flexible to transmit sentences with different semantic information, and achieve better end-to-end performance under various channel conditions.