Neural Coding Is Not Always Semantic: Towards The Standardized Coding Workflow in Semantic Communications

2025-05-24

AI Summary

A fundamental challenge in semantic communication is whether generic features extracted by deep neural networks equate to genuine semantic understanding. This work establishes that “neural encoding ≠ semantic encoding,” clarifying the essential distinction between semantic understanding and generic semantic representation. Method: We propose a standardized definition of semantic encoding and a context-aware framework for generic semantic representation. Our approach integrates context modeling, neural feature disentanglement, lightweight fine-tuning, and regularized adaptation to yield compact, interpretable, and cross-task transferable semantic representations. Contribution/Results: Experiments demonstrate that minimal task-specific adaptation suffices to support diverse human–machine collaborative communication scenarios. The results empirically validate that semantic communication fundamentally entails semantic conveyance—not mere feature transmission—thereby establishing a theoretical foundation and technical paradigm for building trustworthy semantic communication systems.

Technology Category

• Natural Language Processing: Sentence-level Semantics, Textual Inference, etc.
• Cognitive Modeling & Cognitive Systems: Neural Spike Coding
• Multiagent Systems: Agent Communication

Application Category

• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs
• Search and Retrieval-Augmented AI: Web query analysis, representation and understanding
• User Modeling, Personalization and Recommendation: Fairness-aware retrieval and ranking

Abstract

Semantic communication, leveraging advanced deep learning techniques, emerges as a new paradigm that meets the requirements of next-generation wireless networks. However, current semantic communication systems, which employ neural coding for feature extraction from raw data, have not adequately addressed the fundamental question: Is general feature extraction through deep neural networks sufficient for understanding semantic meaning within raw data in semantic communication? This article is thus motivated to clarify two critical aspects: semantic understanding and general semantic representation. This article presents a standardized definition on semantic coding, an extensive neural coding scheme for general semantic representation that clearly represents underlying data semantics based on contextual modeling. With these general semantic representations obtained, both human- and machine-centric end-to-end data transmission can be achieved through only minimal specialized modifications, such as fine-tuning and regularization. This article contributes to establishing a commonsense that semantic communication extends far beyond mere feature transmission, focusing instead on conveying compact semantic representations through context-aware coding schemes.

Problem

• Clarifying semantic understanding in neural coding systems
• Defining standardized semantic coding for contextual data representation
• Enabling versatile human-machine transmission via compact semantic representations

Innovation

• Standardized semantic coding definition
• Context-aware neural coding scheme
• Minimal specialized modifications transmission