mlsanityData to 7 Oct 2026

Non-autoregressive Machine Translation with Probabilistic Context-free Grammar

arXiv 2311.07941 ↗First posted 14 Nov 2023cs.CL cs.AIcited by 4

Not on the map. Why?

Abstract (arXiv)

Non-autoregressive Transformer(NAT) significantly accelerates the inference of neural machine translation. However, conventional NAT models suffer from limited expression power and performance degradation compared to autoregressive (AT) models due to the assumption of conditional independence among target tokens. To address these limitations, we propose a novel approach called PCFG-NAT, which leverages a specially designed Probabilistic Context-Free Grammar (PCFG) to enhance the ability of NAT models to capture complex dependencies among output tokens. Experimental results on major machine translation benchmarks demonstrate that PCFG-NAT further narrows the gap in translation quality between NAT and AT models. Moreover, PCFG-NAT facilitates a deeper understanding of the generated sentences, addressing the lack of satisfactory explainability in neural machine translation.Code is publicly available at https://github.com/ictnlp/PCFG-NAT.

Key facts. Cited by 4 papers in the map (data through 7 Oct 2026). Builds on 31 of its 42 references that are in the map. First posted on arXiv 14 Nov 2023.

Builds on

31 of 42 references.

References · 31

  1. 2017Attention Is All You Needcited by 59,932
  2. 2015Neural Machine Translation of Rare Words with Subword Unitscited by 2,898
  3. 2018A Call for Clarity in Reporting BLEU Scorescited by 1,790
  4. 2019fairseq: A Fast, Extensible Toolkit for Sequence Modelingcited by 1,486
  5. 2017Non-Autoregressive Neural Machine Translationcited by 457
  6. 2018Fast Decoding in Sequence Models using Discrete Latent Variablescited by 103
  7. 2020Glancing Transformer for Non-Autoregressive Neural Machine Translationcited by 103
  8. 2020Fully Non-autoregressive Neural Machine Translation: Tricks of the Tradecited by 99
  9. 2020Non-Autoregressive Machine Translation with Latent Alignmentscited by 96
  10. 2019FlowSeq: Non-Autoregressive Conditional Sequence Generation with Generative Flowcited by 89
  11. 2018End-to-End Non-Autoregressive Neural Machine Translation with Connectionist Temporal Classificationcited by 72
  12. 2020Aligned Cross Entropy for Non-Autoregressive Machine Translationcited by 65
19 more
  1. 2019Latent-Variable Non-Autoregressive Neural Machine Translation with Deterministic Inference Using a Delta Posteriorcited by 58
  2. 2021Order-Agnostic Cross Entropy for Non-Autoregressive Machine Translationcited by 57
  3. 2018Theory and Experiments on Vector Quantized Autoencoderscited by 55
  4. 2022Directed Acyclic Transformer for Non-Autoregressive Machine Translationcited by 44
  5. 2019Guiding Non-Autoregressive Neural Machine Translation Decoding with Reordering Informationcited by 37
  6. 2020Semi-Autoregressive Training Improves Mask-Predict Decodingcited by 33
  7. 2021Sequence-to-Sequence Learning with Latent Neural Grammarscited by 30
  8. 2021Non-Autoregressive Translation by Learning Target Categorical Codescited by 25
  9. 2021AligNART: Non-autoregressive Neural Machine Translation by Jointly Learning to Estimate Alignment and Translatecited by 24
  10. 2022textitlatent-GLAT: Glancing at Latent Variables for Parallel Text Generationcited by 20
  11. 2017Towards String-to-Tree Neural Machine Translationcited by 19
  12. 2019Syntactically Supervised Transformers for Faster Neural Machine Translationcited by 19
  13. 2020Non-Autoregressive Machine Translation with Disentangled Context Transformercited by 13
  14. 2021Enriching Non-Autoregressive Transformer with Syntactic and SemanticStructures for Neural Machine Translationcited by 13
  15. 2022Viterbi Decoding of Directed Acyclic Transformer for Non-Autoregressive Machine Translationcited by 13
  16. 2023Fuzzy Alignments in Directed Acyclic Graph for Non-Autoregressive Machine Translationcited by 11
  17. 2023DASpeech: Directed Acyclic Transformer for Fast and High-quality Speech-to-Speech Translationcited by 9
  18. 2022Hierarchical Phrase-based Sequence-to-Sequence Learningcited by 7
  19. 2022A Study of Syntactic Multi-Modality in Non-Autoregressive Machine Translationcited by 5

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2024: 2; 2025: 1; 2026: 1.

4 papers.

  1. 2025Continuous Autoregressive Language Modelscited by 9
  2. 2024Beyond Next Token Prediction: Patch-Level Training for Large Language Modelscited by 7
  3. 2024COrAL: Order-Agnostic Language Modeling for Efficient Iterative Refinementcited by 3
  4. 2026Fully Rotation-Equivariant Spectral-Spatial Learning for Multispectral Object Detectioncited by 0