mlsanityData to 7 Oct 2026

Semi-Autoregressive Neural Machine Translation

arXiv 1808.08583 ↗First posted 26 Aug 2018cs.CLcited by 48

Not on the map. Why?

Abstract (arXiv)

Existing approaches to neural machine translation are typically autoregressive models. While these models attain state-of-the-art translation quality, they are suffering from low parallelizability and thus slow at decoding long sequences. In this paper, we propose a novel model for fast sequence generation --- the semi-autoregressive Transformer (SAT). The SAT keeps the autoregressive property in global but relieves in local and thus is able to produce multiple successive words in parallel at each time step. Experiments conducted on English-German and Chinese-English translation tasks show that the SAT achieves a good balance between translation quality and decoding speed. On WMT'14 English-German translation, the SAT achieves 5.58× speedup while maintains 88% translation quality, significantly better than the previous non-autoregressive methods. When produces two words at each time step, the SAT is almost lossless (only 1% degeneration in BLEU score).

Key facts. Cited by 48 papers in the map (data through 7 Oct 2026). First posted on arXiv 26 Aug 2018.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 8; 2022: 9; 2023: 8; 2024: 10; 2025: 5; 2026: 8.

48 papers.

Sort:

By area:

  1. 2022Diffusion-LM Improves Controllable Text Generationcited by 1,006
  2. 2022SSD-LM: Semi-autoregressive Simplex-based Diffusion Language Model for Text Generation and Modular Controlcited by 191
  3. 2023Accelerating Transformer Inference for Translation via Parallel Decodingcited by 123
  4. 2025Accelerating Diffusion LLMs via Adaptive Parallel Decodingcited by 108
  5. 2022A Survey on Non-Autoregressive Generation for Neural Machine Translation and Beyondcited by 64
  6. 2024Parallelized Autoregressive Visual Generationcited by 58
  7. 2022Generative Knowledge Graph Construction: A Reviewcited by 49
  8. 2021FastCorrect: Fast Error Correction with Edit Alignment for Automatic Speech Recognitioncited by 43
  9. 2021Non-Autoregressive Translation with Layer-Wise Prediction and Deep Supervisioncited by 40
  10. 2025Next Block Prediction: Video Generation via Semi-Autoregressive Modelingcited by 26
  11. 2024Generation Meets Verification: Accelerating Large Language Model Inference with Smart Parallel Auto-Correct Decodingcited by 22
  12. 2024Falcon: Faster and Parallel Inference of Large Language Models through Enhanced Semi-Autoregressive Drafting and Custom-Designed Decoding Treecited by 20
36 more
  1. 2021Sequence-Level Training for Non-Autoregressive Neural Machine Translationcited by 18
  2. 2022Lossless Acceleration for Seq2seq Generation with Aggressive Decodingcited by 18
  3. 2022Viterbi Decoding of Directed Acyclic Transformer for Non-Autoregressive Machine Translationcited by 13
  4. 2023Candidate Soups: Fusing Candidate Results Improves Translation Quality for Non-Autoregressive Translationcited by 13
  5. 2024BiTA: Bi-Directional Tuning for Lossless Acceleration in Large Language Modelscited by 13
  6. 2021Semi-Autoregressive Transformer for Image Captioningcited by 12
  7. 2023Fuzzy Alignments in Directed Acyclic Graph for Non-Autoregressive Machine Translationcited by 11
  8. 2021Semi-Autoregressive Image Captioningcited by 10
  9. 2023Can Diffusion Model Achieve Better Performance in Text Generation? Bridging the Gap between Training and Inference!cited by 10
  10. 2024The Mystery of the Pathological Path-star Task for Language Modelscited by 8
  11. 2021Improving Non-autoregressive Generation with Mixup Trainingcited by 7
  12. 2023Non-Autoregressive Math Word Problem Solver with Unified Tree Structurecited by 7
  13. 2024Look Ahead or Look Around? A Theoretical Comparison Between Autoregressive and Masked Pretrainingcited by 7
  14. 2025PRIM: Towards Practical In-Image Multilingual Machine Translationcited by 7
  15. 2026When to Commit? Towards Variable-Size Self-Contained Blocks for Discrete Diffusion Language Modelscited by 7
  16. 2022Uncertainty-Aware Image Captioningcited by 6
  17. 2023Semi-Autoregressive Streaming ASR With Label Contextcited by 5
  18. 2024Non-autoregressive Sequence-to-Sequence Vision-Language Modelscited by 5
  19. 2024A Comprehensive Survey of Accelerated Generation Techniques in Large Language Modelscited by 5
  20. 2021Modeling Coverage for Non-Autoregressive Neural Machine Translationcited by 4
  21. 2022Hybrid-Regressive Neural Machine Translationcited by 3
  22. 2024Translating Images to Road Network: A Sequence-to-Sequence Perspectivecited by 3
  23. 2025Multi-Amateur Contrastive Decoding for Text Generationcited by 3
  24. 2026From Static Inference to Dynamic Interaction: A Survey of Streaming Large Language Modelscited by 3
  25. 2026Efficient Personalized Reranking with Semi-Autoregressive Generation and Online Knowledge Distillationcited by 3
  26. 2023TreePiece: Faster Semantic Parsing via Tree Tokenizationcited by 2
  27. 2024Bidirectional Awareness Induction in Autoregressive Seq2Seq Modelscited by 2
  28. 2026From Chains to Trees: Parent-Conditioned Drafting for Semi-Autoregressive Speculative Decodingcited by 2
  29. 2023Progressive Neural Network for Multi-Horizon Time Series Forecastingcited by 1
  30. 2026VDLM: Variable Diffusion LMs via Robust Latent-to-Text Renderingcited by 1
  31. 2021Learning and Analyzing Generation Order for Undirected Sequence Modelscited by 0
  32. 2022The RoyalFlush System for the WMT 2022 Efficiency Taskcited by 0
  33. 2025RTGen: Real-Time Generative Detection Transformercited by 0
  34. 2026BitLM: Unlocking Multi-Token Language Generation with Bitwise Continuous Diffusioncited by 0
  35. 2026Fully Rotation-Equivariant Spectral-Spatial Learning for Multispectral Object Detectioncited by 0
  36. 2026JevSpawn: Adaptive Agentic Inference through Compositional Action Spacescited by 0