发表机构
The University of Sydney（悉尼大学）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
针对带噪无线信道的自然语言文本传输，本文提出含信道解码器、语言模型及解交织器的迭代语义接收机，在SNLI语料库AWGN信道仿真中，其BLER较传统短分组编码提升约1.5 dB，且SNR超1.0 dB时BLEU、ROUGE均超99%。
AI 中文摘要
本文针对通过带噪无线信道传输自然语言文本的场景，提出了一种经迭代增强的语义接收机，该接收机采用多个短分组码实现传输。在发射端，每个句子经字符级交织器置换后被划分为多个分段，各分段由短分组码独立编码。在接收端，我们开发了一种由信道解码器和语言模型构成的迭代解码器，二者之间的解交织器可将每个分段内的突发解码错误分散到整个句子中。每一轮迭代中，语言模型对信道解码输出进行去噪，经去噪且与信道观测结果一致的字符会作为语义信息反馈给信道解码器，用于下一轮迭代。在加性高斯白噪声（AWGN）信道下基于斯坦福自然语言推理（SNLI）语料库的仿真结果表明，所提出的接收机相较于传统短分组编码，在分组错误率（BLER）上实现了约1.5 dB的增益，且在信噪比（SNR）超过1.0 dB时，BLEU和ROUGE分数均保持在99%以上。
英文摘要
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.
Comments5 pages, 4 figures
