mlsanityData to 14 Oct 2026

Importance-Aware Data Augmentation for Document-Level Neural Machine Translation

arXiv 2401.15360 ↗First posted 27 Jan 2024cs.CLcited by 4

Not on the map. Why?

Abstract (arXiv)

Document-level neural machine translation (DocNMT) aims to generate translations that are both coherent and cohesive, in contrast to its sentence-level counterpart. However, due to its longer input length and limited availability of training data, DocNMT often faces the challenge of data sparsity. To overcome this issue, we propose a novel Importance-Aware Data Augmentation (IADA) algorithm for DocNMT that augments the training data based on token importance information estimated by the norm of hidden states and training gradients. We conduct comprehensive experiments on three widely-used DocNMT benchmarks. Our empirical results show that our proposed IADA outperforms strong DocNMT baselines as well as several data augmentation approaches, with statistical significance on both sentence-level and document-level BLEU.

Key facts. Cited by 4 papers in the map (data through 14 Oct 2026). Builds on 37 of its 57 references that are in the map. First posted on arXiv 27 Jan 2024.

Builds on

37 of 57 references.

References · 37

  1. 2017Attention Is All You Needcited by 60,361
  2. 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,399
  3. 2014Adam: A Method for Stochastic Optimizationcited by 37,240
  4. 2016Layer Normalizationcited by 5,669
  5. 2015Neural Machine Translation of Rare Words with Subword Unitscited by 2,918
  6. 2018Deep contextualized word representationscited by 2,290
  7. 2020Multilingual Denoising Pre-training for Neural Machine Translationcited by 1,035
  8. 2019EDA: Easy Data Augmentation Techniques for Boosting Performance on Text Classification Taskscited by 807
  9. 2015Improving Neural Machine Translation Models with Monolingual Datacited by 788
  10. 2018Subword Regularization: Improving Neural Network Translation Models with Multiple Subword Candidatescited by 639
  11. 2020Dataset Cartography: Mapping and Diagnosing Datasets with Training Dynamicscited by 425
  12. 2019BPE-Dropout: Simple and Effective Subword Regularizationcited by 195
25 more
  1. 2015A Theoretically Grounded Application of Dropout in Recurrent Neural Networkscited by 161
  2. 2019Revisiting Self-Training for Neural Sequence Generationcited by 155
  3. 2017Neural Machine Translation with Extended Contextcited by 95
  4. 2017Evaluating Discourse Phenomena in Neural Machine Translationcited by 87
  5. 2018Document-Level Neural Machine Translation with Hierarchical Attention Networkscited by 85
  6. 2016Edinburgh Neural Machine Translation Systems for WMT 16cited by 76
  7. 2019Selective Attention for Context-aware Neural Machine Translationcited by 60
  8. 2021The paradox of the compositionality of natural language: a neural machine translation case studycited by 59
  9. 2024Adapting Large Language Models for Document-Level Machine Translationcited by 59
  10. 2021BlonDe: An Automatic Evaluation Metric for Document-level Machine Translationcited by 58
  11. 2022PromDA: Prompt-based Data Augmentation for Low-Resource NLU Taskscited by 51
  12. 2021Measuring and Increasing Context Usage in Context-Aware Machine Translationcited by 48
  13. 2021G-Transformer for Document-level Machine Translationcited by 46
  14. 2019Towards Making the Most of BERT in Neural Machine Translationcited by 43
  15. 2017Document Context Neural Machine Translation with Memory Networkscited by 41
  16. 2020Diving Deep into Context-Aware Neural Machine Translationcited by 25
  17. 2015Measuring Word Significance using Distributed Representations of Wordscited by 21
  18. 2021Uncertainty-Aware Balancing for Multilingual and Multi-Domain Neural Machine Translation Trainingcited by 19
  19. 2021Rethinking Perturbations in Encoder-Decoders for Fast Trainingcited by 17
  20. 2023Document Flattening: Beyond Concatenating Context for Document-Level Neural Machine Translationcited by 15
  21. 2020Contextual Neural Machine Translation Improves Translation of Cataphoric Pronounscited by 13
  22. 2021Divide and Rule: Effective Pre-Training for Context-Aware Multi-Encoder Translation Modelscited by 12
  23. 2021Consistency Training with Virtual Adversarial Discrete Perturbationcited by 9
  24. 2022CipherDAug: Ciphertext based Data Augmentation for Neural Machine Translationcited by 9
  25. 2015Controlled Experiments for Word Embeddingscited by 5

Built on by

Cited by year

Citing papers per year: 2024: 3; 2025: 1.

4 papers.

  1. 2024(Perhaps) Beyond Human Translation: Harnessing Multi-Agent Collaboration for Translating Ultra-Long Literary Textscited by 49
  2. 2025Multilingual Contextualization of Large Language Models for Document-Level Machine Translationcited by 11
  3. 2024Fine-Grained and Multi-Dimensional Metrics for Document-Level Machine Translationcited by 10
  4. 2024Investigating Length Issues in Document-level Machine Translationcited by 10