mlsanityData to 7 Oct 2026

End-to-End Non-Autoregressive Neural Machine Translation with Connectionist Temporal Classification

arXiv 1811.04719 ↗First posted 12 Nov 2018cs.CLcited by 72

Not on the map. Why?

Abstract (arXiv)

Autoregressive decoding is the only part of sequence-to-sequence models that prevents them from massive parallelization at inference time. Non-autoregressive models enable the decoder to generate all output symbols independently in parallel. We present a novel non-autoregressive architecture based on connectionist temporal classification and evaluate it on the task of neural machine translation. Unlike other non-autoregressive methods which operate in several steps, our model can be trained end-to-end. We conduct experiments on the WMT English-Romanian and English-German datasets. Our models achieve a significant speedup over the autoregressive models, keeping the translation quality comparable to other non-autoregressive models.

Key facts. Cited by 72 papers in the map (data through 7 Oct 2026). First posted on arXiv 12 Nov 2018.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 15; 2022: 28; 2023: 16; 2024: 7; 2025: 3; 2026: 3.

72 papers.

Sort:

By area:

  1. 2022Speculative Decoding: Exploiting Speculative Execution for Accelerating Seq2seq Generationcited by 169
  2. 2022A Survey on Non-Autoregressive Generation for Neural Machine Translation and Beyondcited by 64
  3. 2021Order-Agnostic Cross Entropy for Non-Autoregressive Machine Translationcited by 57
  4. 2022Directed Acyclic Transformer for Non-Autoregressive Machine Translationcited by 44
  5. 2021A Comparative Study on Non-Autoregressive Modelings for Speech-to-Text Generationcited by 27
  6. 2022On the Learning of Non-Autoregressive Transformerscited by 27
  7. 2025A Survey on Parallel Text Generation: From Parallel Decoding to Diffusion Language Modelscited by 27
  8. 2022Revisiting End-to-End Speech-to-Text Translation From Scratchcited by 26
  9. 2022CTC Alignments Improve Autoregressive Translationcited by 25
  10. 2021Investigating the Reordering Capability in CTC-based Non-Autoregressive End-to-End Speech Translationcited by 23
  11. 2022One Reference Is Not Enough: Diverse Distillation with Reference Selection for Non-Autoregressive Translationcited by 20
  12. 2021Sequence-Level Training for Non-Autoregressive Neural Machine Translationcited by 18
38 more
  1. 2022Lossless Acceleration for Seq2seq Generation with Aggressive Decodingcited by 18
  2. 2022Non-Monotonic Latent Alignments for CTC-Based Non-Autoregressive Machine Translationcited by 16
  3. 2021Enriching Non-Autoregressive Transformer with Syntactic and SemanticStructures for Neural Machine Translationcited by 13
  4. 2022Viterbi Decoding of Directed Acyclic Transformer for Non-Autoregressive Machine Translationcited by 13
  5. 2023Candidate Soups: Fusing Candidate Results Improves Translation Quality for Non-Autoregressive Translationcited by 13
  6. 2023Non-autoregressive Streaming Transformer for Simultaneous Translationcited by 12
  7. 2021Streaming End-to-End ASR based on Blockwise Non-Autoregressive Modelscited by 11
  8. 2022Non-Autoregressive Machine Translation: It's Not as Fast as it Seemscited by 11
  9. 2023Fuzzy Alignments in Directed Acyclic Graph for Non-Autoregressive Machine Translationcited by 11
  10. 2025ToolACE-MT: Non-Autoregressive Generation for Agentic Multi-Turn Interactioncited by 11
  11. 2022ELMER: A Non-Autoregressive Pre-trained Language Model for Efficient and Effective Text Generationcited by 10
  12. 2021Duplex Sequence-to-Sequence Learning for Reversible Machine Translationcited by 9
  13. 2021Non-autoregressive End-to-end Speech Translation with Parallel Autoregressive Rescoringcited by 9
  14. 2022LegoNN: Building Modular Encoder-Decoder Modelscited by 9
  15. 2022SoftCorrect: Error Correction with Soft Detection for Automatic Speech Recognitioncited by 9
  16. 2023CTC-based Non-autoregressive Speech Translationcited by 9
  17. 2023DASpeech: Directed Acyclic Transformer for Fast and High-quality Speech-to-Speech Translationcited by 9
  18. 2023Simultaneous Machine Translation with Tailored Referencecited by 9
  19. 2021A Streaming End-to-End Framework For Spoken Language Understandingcited by 8
  20. 2022ngram-OAXE: Phrase-Based Order-Agnostic Cross Entropy for Non-Autoregressive Machine Translationcited by 8
  21. 2023Directed Acyclic Transformer Pre-training for High-quality Non-autoregressive Text Generationcited by 8
  22. 2023Non-autoregressive Text Editing with Copy-aware Latent Alignmentscited by 8
  23. 2022An Efficient Framework for Few-shot Skeleton-based Temporal Action Segmentationcited by 7
  24. 2024Beyond Next Token Prediction: Patch-Level Training for Large Language Modelscited by 7
  25. 2022Multi-Granularity Optimization for Non-Autoregressive Translationcited by 6
  26. 2022Anticipation-Free Training for Simultaneous Machine Translationcited by 5
  27. 2022Non-Autoregressive Neural Machine Translation: A Call for Claritycited by 5
  28. 2022A Study of Syntactic Multi-Modality in Non-Autoregressive Machine Translationcited by 5
  29. 2022Integrating Translation Memories into Non-Autoregressive Machine Translationcited by 5
  30. 2024Non-autoregressive Sequence-to-Sequence Vision-Language Modelscited by 5
  31. 2021Modeling Coverage for Non-Autoregressive Neural Machine Translationcited by 4
  32. 2023Non-autoregressive Machine Translation with Probabilistic Context-free Grammarcited by 4
  33. 2021Can Latent Alignments Improve Autoregressive Machine Translation?cited by 3
  34. 2022DePA: Improving Non-autoregressive Machine Translation with Dependency-Aware Decodercited by 3
  35. 2022Improving Top-K Decoding for Non-Autoregressive Semantic Parsing via Intent Conditioningcited by 3
  36. 2022Rephrasing the Reference for Non-Autoregressive Machine Translationcited by 3
  37. 2022Diffusion Glancing Transformer for Parallel Sequence to Sequence Learningcited by 3
  38. 2023TreePiece: Faster Semantic Parsing via Tree Tokenizationcited by 2

50 most cited of 72 All 72 (JSON)