Semantic Error Correction and Decoding for Short Block Channel Codes

2026-04-24

AI Summary

This work addresses the challenge of simultaneously achieving semantic fidelity and robust error correction in short-blocklength communication over noisy wireless channels. The authors propose a semantic-aware short-blocklength coding framework that segments sentences into short blocks for independent transmission and employs a BART-based bidirectional-autoregressive Transformer at the receiver to perform context-aware semantic error correction. The framework integrates semantic list decoding and a confidence-guided HARQ mechanism without CRC overhead (termed SHARQ). By deeply embedding semantic information into the short-blocklength system, the approach significantly enhances performance while maintaining low latency: it achieves a 0.8 dB gain in block error rate (BLER) over conventional short codes, reduces decoding latency by 90% compared to 5G LDPC long codes while substantially improving semantic fidelity, and yields an additional 1.5 dB gain through the SHARQ mechanism.

Technology Category

• Machine Learning: Hardware-aware ML
• Natural Language Processing: Sentence-level Semantics, Textual Inference, etc.
• Cognitive Modeling & Cognitive Systems: Neural Spike Coding

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: Large language models for search
• Systems and Infrastructure for Web, Mobile and WoT: Applied ML and AI for Web-based mobile applications

Abstract

This paper presents a semantic-enhanced receiver framework for transmitting natural language sentences over noisy wireless channels using multiple short block codes. After ASCII encoding, the sentence is divided into segments, each independently encoded with a short block code and transmitted over an AWGN channel. At the receiver, segments are decoded in parallel, followed by a semantic error correction (SEC) model, which reconstructs corrupted segments using language model context. We further propose the semantic list decoding (SLD), which generates multiple candidate reconstructions and selects the best one via weighted Hamming distance, and a semantic confidence-guided HARQ (SHARQ) mechanism that replaces CRC-based error detection with a confidence score, enabling selective segment retransmission without CRC overhead. All modules are designed and trained using bidirectional and auto-regressive transformers (BART). Simulation results demonstrate that the proposed scheme significantly outperforms conventional capacity-approaching short codes and long codes at the same rate. Specifically, SEC provides approximately 0.4 dB BLER gain over plain short-code transmission, while SLD extends this to 0.8 dB. Compared to transmitting the entire sentence as a single long 5G LDPC codeword, our approach significantly improves semantic fidelity and reduces decoding latency by up to 90\%. SHARQ further provides an additional 1.5 dB gain over conventional HARQ.

Problem

• semantic error correction
• short block codes
• wireless communication
• natural language transmission
• decoding latency

Innovation

• Semantic Error Correction
• Semantic List Decoding
• Confidence-guided HARQ
• Short Block Codes
• BART-based Receiver