mlsanityData to 7 Oct 2026

Imputer: Sequence Modelling via Imputation and Dynamic Programming

arXiv 2002.08926 ↗First posted 20 Feb 2020eess.AS cs.CL cs.LGcited by 65

Not on the map. Why?

Abstract (arXiv)

This paper presents the Imputer, a neural sequence model that generates output sequences iteratively via imputations. The Imputer is an iterative generative model, requiring only a constant number of generation steps independent of the number of input or output tokens. The Imputer can be trained to approximately marginalize over all possible alignments between the input and output sequences, and all possible generation orders. We present a tractable dynamic programming training algorithm, which yields a lower bound on the log marginal likelihood. When applied to end-to-end speech recognition, the Imputer outperforms prior non-autoregressive models and achieves competitive results to autoregressive models. On LibriSpeech test-other, the Imputer achieves 11.1 WER, outperforming CTC at 13.0 WER and seq2seq at 12.5 WER.

Key facts. Cited by 65 papers in the map (data through 7 Oct 2026). First posted on arXiv 20 Feb 2020.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 25; 2022: 18; 2023: 12; 2024: 4; 2025: 5; 2026: 1.

65 papers.

Sort:

By area:

  1. 2021Structured Denoising Diffusion Models in Discrete State-Spacescited by 1,665
  2. 2022Continuous diffusion for categorical datacited by 202
  3. 2021Instances as Queriescited by 157
  4. 2021Learning to Efficiently Sample from Diffusion Probabilistic Modelscited by 129
  5. 2023End-to-End Speech Recognition: A Surveycited by 127
  6. 2021Step-unrolled Denoising Autoencoders for Text Generationcited by 102
  7. 2021Intermediate Loss Regularization for CTC-based Speech Recognitioncited by 95
  8. 2021SpeechStew: Simply Mix All Available Speech Recognition Data to Train One Large Neural Networkcited by 83
  9. 2021Unleashing Transformers: Parallel Token Prediction with Discrete Absorbing Diffusion for Fast High-Resolution Image Generation from Vector-Quantized Codescited by 71
  10. 2022A Survey on Non-Autoregressive Generation for Neural Machine Translation and Beyondcited by 64
  11. 2021Relaxing the Conditional Independence Assumption of CTC-based ASR by Conditioning on Intermediate Predictionscited by 61
  12. 2025Edit Flows: Flow Matching with Edit Operationscited by 53
38 more
  1. 2021PIMNet: A Parallel, Iterative and Mimicking Network for Scene Text Recognitioncited by 41
  2. 2021Non-Autoregressive Translation with Layer-Wise Prediction and Deep Supervisioncited by 40
  3. 2021A Comparative Study on Non-Autoregressive Modelings for Speech-to-Text Generationcited by 27
  4. 2022CTC Alignments Improve Autoregressive Translationcited by 25
  5. 2021Investigating the Reordering Capability in CTC-based Non-Autoregressive End-to-End Speech Translationcited by 23
  6. 2021Beyond In-Place Corruption: Insertion and Deletion In Denoising Probabilistic Modelscited by 23
  7. 2022An Imitation Learning Curriculum for Text Editing with Non-Autoregressive Modelscited by 20
  8. 2021Pushing the Limits of Non-Autoregressive Speech Recognitioncited by 18
  9. 2022Improving CTC-based speech recognition via knowledge transferring from pre-trained language modelscited by 14
  10. 2021Layer Pruning on Demand with Intermediate CTCcited by 13
  11. 2021Deliberation of Streaming RNN-Transducer by Non-autoregressive Decodingcited by 13
  12. 2022Learning Non-Autoregressive Models from Search for Unsupervised Sentence Summarizationcited by 12
  13. 2023IPAD: Iterative, Parallel, and Diffusion-based Network for Scene Text Recognitioncited by 12
  14. 2021Streaming End-to-End ASR based on Blockwise Non-Autoregressive Modelscited by 11
  15. 2022BERT Meets CTC: New Formulation of End-to-End Speech Recognition with Pre-trained Masked Language Modelcited by 11
  16. 2021Non-autoregressive End-to-end Speech Translation with Parallel Autoregressive Rescoringcited by 9
  17. 2022LegoNN: Building Modular Encoder-Decoder Modelscited by 9
  18. 2023CTC-based Non-autoregressive Speech Translationcited by 9
  19. 2021Non-autoregressive Mandarin-English Code-switching Speech Recognitioncited by 8
  20. 2021An Improved Single Step Non-autoregressive Transformer for Automatic Speech Recognitioncited by 8
  21. 2022BECTRA: Transducer-based End-to-End ASR with BERT-Enhanced Encodercited by 8
  22. 2023Non-autoregressive Text Editing with Copy-aware Latent Alignmentscited by 8
  23. 2022Uncertainty-Aware Image Captioningcited by 6
  24. 2024Promises and Pitfalls of Generative Masked Language Modeling: Theoretical Framework and Practical Guidelinescited by 6
  25. 2022InterAug: Augmenting Noisy Intermediate Predictions for CTC-based ASRcited by 5
  26. 2022Better Intermediates Improve CTC Inferencecited by 5
  27. 2022Non-Autoregressive Neural Machine Translation: A Call for Claritycited by 5
  28. 2023A CTC Alignment-based Non-autoregressive Transformer for End-to-end Automatic Speech Recognitioncited by 5
  29. 2022Improving Top-K Decoding for Non-Autoregressive Semantic Parsing via Intent Conditioningcited by 3
  30. 2024Muscles in Time: Learning to Understand Human Motion by Simulating Muscle Activationscited by 3
  31. 2022Text Detection & Recognition in the Wild for Robot Localizationcited by 2
  32. 2022PARAGEN : A Parallel Generation Toolkitcited by 2
  33. 2023Dynamic Alignment Mask CTC: Improved Mask-CTC with Aligned Cross Entropycited by 2
  34. 2023MixRep: Hidden Representation Mixup for Low-Resource Speech Recognitioncited by 2
  35. 2021Investigating transformers in the decomposition of polygonal shapes as point collectionscited by 1
  36. 2021SimpleTRON: Simple Transformer with O(N) Complexitycited by 1
  37. 2021Can Multilinguality benefit Non-autoregressive Machine Translation?cited by 1
  38. 2022Streaming Align-Refine for Non-autoregressive Deliberationcited by 1

50 most cited of 65 All 65 (JSON)