mlsanityData to 14 Oct 2026

Neighbors Are Not Strangers: Improving Non-Autoregressive Translation under Low-Frequency Lexical Constraints

arXiv 2204.13355 ↗First posted 28 Apr 2022cs.CLcited by 3

Not on the map. Why?

Abstract (arXiv)

However, current autoregressive approaches suffer from high latency. In this paper, we focus on non-autoregressive translation (NAT) for this problem for its efficiency advantage. We identify that current constrained NAT models, which are based on iterative editing, do not handle low-frequency constraints well. To this end, we propose a plug-in algorithm for this line of work, i.e., Aligned Constrained Training (ACT), which alleviates this problem by familiarizing the model with the source-side context of the constraints. Experiments on the general and domain datasets show that our model improves over the backbone constrained NAT model in constraint preservation and translation quality, especially for rare constraints.

Key facts. Cited by 3 papers in the map (data through 14 Oct 2026). Builds on 30 of its 44 references that are in the map. First posted on arXiv 28 Apr 2022.

Builds on

30 of 44 references.

References · 30

  1. 2017Attention Is All You Needcited by 60,361
  2. 2014Adam: A Method for Stochastic Optimizationcited by 37,240
  3. 2014Neural Machine Translation by Jointly Learning to Align and Translatecited by 4,548
  4. 2015Neural Machine Translation of Rare Words with Subword Unitscited by 2,918
  5. 2019fairseq: A Fast, Extensible Toolkit for Sequence Modelingcited by 1,488
  6. 2016Sequence-Level Knowledge Distillationcited by 801
  7. 2017Non-Autoregressive Neural Machine Translationcited by 463
  8. 2017Lexically Constrained Decoding for Sequence Generation Using Grid Beam Searchcited by 237
  9. 2018Scaling Neural Machine Translationcited by 204
  10. 2019Levenshtein Transformercited by 199
  11. 2018Fast Lexically Constrained Decoding with Dynamic Beam Allocation for Neural Machine Translationcited by 182
  12. 2019Insertion Transformer: Flexible Sequence Generation via Insertion Operationscited by 125
18 more
  1. 2019Understanding Knowledge Distillation in Non-autoregressive Machine Translationcited by 122
  2. 2018Fast Decoding in Sequence Models using Discrete Latent Variablescited by 104
  3. 2020Glancing Transformer for Non-Autoregressive Neural Machine Translationcited by 103
  4. 2019Training Neural Machine Translation To Apply Terminology Constraintscited by 73
  5. 2019Latent-Variable Non-Autoregressive Neural Machine Translation with Deterministic Inference Using a Delta Posteriorcited by 58
  6. 2021Order-Agnostic Cross Entropy for Non-Autoregressive Machine Translationcited by 57
  7. 2020Understanding and Improving Lexical Choice in Non-Autoregressive Translationcited by 56
  8. 2019Code-Switching for Enhancing NMT with Pre-Specified Translationcited by 53
  9. 2019Non-Autoregressive Machine Translation with Auxiliary Regularizationcited by 52
  10. 2014Addressing the Rare Word Problem in Neural Machine Translationcited by 50
  11. 2020Lexically Constrained Neural Machine Translation with Levenshtein Transformercited by 45
  12. 2020Incorporating BERT into Parallel Sequence Decoding with Adapterscited by 39
  13. 2016SYSTRAN's Pure Neural Machine Translation Systemscited by 24
  14. 2020EDITOR: an Edit-Based Transformer with Repositioning for Neural Machine Translation with Soft Lexical Constraintscited by 24
  15. 2018On The Alignment Problem In Multi-Head Attention-Based Neural Machine Translationcited by 17
  16. 2021How Does Distilled Data Complexity Impact the Quality and Confidence of Non-Autoregressive Machine Translation?cited by 12
  17. 2021Encouraging Neural Machine Translation to Satisfy Terminology Constraintscited by 10
  18. 2021Improving Lexically Constrained Neural Machine Translation with Source-Conditioned Masked Span Predictioncited by 3

Built on by

Cited by year

Citing papers per year: 2022: 2; 2023: 1.

3 papers.

  1. 2022Integrating Translation Memories into Non-Autoregressive Machine Translationcited by 5
  2. 2022Harnessing Knowledge and Reasoning for Human-Like Natural Language Generation: A Brief Reviewcited by 3
  3. 2023Towards Accurate Translation via Semantically Appropriate Application of Lexical Constraintscited by 3