Generative Semantic HARQ: Latent-Space Text Retransmission and Combining
Fuente:
arXiv
Guardado en:
| Autores principales: | , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2026
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866911518920015872 |
|---|---|
| author | Han, Bin Hu, Yulin Schotten, Hans D. |
| author_facet | Han, Bin Hu, Yulin Schotten, Hans D. |
| contents | Semantic communication conveys meaning rather than raw bits, but reliability at the semantic level remains an open challenge. We propose a semantic-level hybrid automatic repeat request (HARQ) framework for text communication, in which a Transformer-variational autoencoder (VAE) codec operates as a lightweight overlay on the conventional protocol stack. The stochastic encoder inherently generates diverse latent representations across retransmissions-providing incremental knowledge (IK) from a single model without dedicated protocol design. On the receiver side, a soft quality estimator triggers retransmissions and a quality-aware combiner merges the received latent vectors within a consistent latent space. We systematically benchmark six semantic quality metrics and four soft combining strategies under hybrid semantic distortion that mixes systematic bias with additive noise. The results suggest combining Weighted-Average or MRC-Inspired combining with self-consistency-based HARQ triggering for the best performance. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2603_15068 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | Generative Semantic HARQ: Latent-Space Text Retransmission and Combining Han, Bin Hu, Yulin Schotten, Hans D. Signal Processing Machine Learning Semantic communication conveys meaning rather than raw bits, but reliability at the semantic level remains an open challenge. We propose a semantic-level hybrid automatic repeat request (HARQ) framework for text communication, in which a Transformer-variational autoencoder (VAE) codec operates as a lightweight overlay on the conventional protocol stack. The stochastic encoder inherently generates diverse latent representations across retransmissions-providing incremental knowledge (IK) from a single model without dedicated protocol design. On the receiver side, a soft quality estimator triggers retransmissions and a quality-aware combiner merges the received latent vectors within a consistent latent space. We systematically benchmark six semantic quality metrics and four soft combining strategies under hybrid semantic distortion that mixes systematic bias with additive noise. The results suggest combining Weighted-Average or MRC-Inspired combining with self-consistency-based HARQ triggering for the best performance. |
| title | Generative Semantic HARQ: Latent-Space Text Retransmission and Combining |
| topic | Signal Processing Machine Learning |
| url | https://arxiv.org/abs/2603.15068 |