Problem
Research questions and friction points this paper is trying to address.
iterative decoding
semantic receiver
short block codes
noisy wireless channels
natural-language text transmission
Iterative Semantic Decoding for Short Block Codes
🤖 AI Summary
本文提出了一种迭代增强语义接收器，用于在噪声无线信道中使用多个短块码传输自然语言文本，通过结合信道解码和语言模型提高传输准确性。
📝 Abstract
This paper proposes an iteratively enhanced semantic receiver for natural-language text transmission over noisy wireless channels using multiple short block codes. At the transmitter, each sentence is permuted by a character-level interleaver, partitioned into segments, and independently encoded by short block codes. At the receiver, we develop an iterative decoder consisting of a channel decoder and a language model, where a de-interleaver between them disperses the burst decoding errors within each segment across the sentence. In each iteration, the language model denoises the channel decoding output, and the denoised characters verified to be consistent with the channel observations are fed back to the channel decoder as semantic information for the next iteration. Simulation results on the Stanford Natural Language Inference (SNLI) corpus over the additive white Gaussian noise (AWGN) channel show that the proposed receiver achieves approximately 1.5 dB block error rate (BLER) gain over conventional short-block coding, while maintaining BLEU and ROUGE scores above 99% at SNRs beyond 1.0 dB.
Innovation
Methods, ideas, or system contributions that make the work stand out.
iterative semantic decoding
short block codes
language model
channel decoder
de-interleaver
🔎 Similar Papers
No similar papers found.
