mlsanityData to 7 Oct 2026

Sub-Word Alignment Is Still Useful: A Vest-Pocket Method for Enhancing Low-Resource Machine Translation

arXiv 2205.04067 ↗First posted 9 May 2022cs.CLcited by 3

Not on the map. Why?

Abstract (arXiv)

We leverage embedding duplication between aligned sub-words to extend the Parent-Child transfer learning method, so as to improve low-resource machine translation. We conduct experiments on benchmark datasets of My-En, Id-En and Tr-En translation scenarios. The test results show that our method produces substantial improvements, achieving the BLEU scores of 22.5, 28.0 and 18.1 respectively. In addition, the method is computationally efficient which reduces the consumption of training time by 63.8%, reaching the duration of 1.6 hours when training on a Tesla 16GB P100 GPU. All the models and source codes in the experiments will be made publicly available to support reproducible research.

Key facts. Cited by 3 papers in the map (data through 7 Oct 2026). Builds on 25 of its 35 references that are in the map. First posted on arXiv 9 May 2022.

Builds on

25 of 35 references.

References · 25

  1. 2017Attention Is All You Needcited by 59,932
  2. 2015Neural Machine Translation of Rare Words with Subword Unitscited by 2,898
  3. 2018SentencePiece: A simple and language independent subword tokenizer and detokenizer for Neural Text Processingcited by 1,973
  4. 2018A Call for Clarity in Reporting BLEU Scorescited by 1,790
  5. 2015Improving Neural Machine Translation Models with Monolingual Datacited by 784
  6. 2017Word Translation Without Parallel Datacited by 480
  7. 2016Google's Multilingual Neural Machine Translation System: Enabling Zero-Shot Translationcited by 467
  8. 2017Six Challenges for Neural Machine Translationcited by 334
  9. 2017Unsupervised Machine Translation Using Monolingual Corpora Onlycited by 272
  10. 2016Transfer Learning for Low-Resource Neural Machine Translationcited by 188
  11. 2017Unsupervised Neural Machine Translationcited by 148
  12. 2019Choosing Transfer Languages for Cross-Lingual Learningcited by 143
13 more
  1. 2018Phrase-Based & Neural Unsupervised Machine Translationcited by 138
  2. 2016Multi-Way, Multilingual Neural Machine Translation with a Shared Attention Mechanismcited by 117
  3. 2018Meta-Learning for Low-Resource Neural Machine Translationcited by 105
  4. 2018Universal Neural Machine Translation for Extremely Low Resource Languagescited by 66
  5. 2018On the Limitations of Unsupervised Bilingual Dictionary Inductioncited by 61
  6. 2017Transfer Learning across Low-Resource, Related Languages for Neural Machine Translationcited by 58
  7. 2016Fully Character-Level Neural Machine Translation without Explicit Segmentationcited by 55
  8. 2018Trivial Transfer Learning for Low-Resource Neural Machine Translationcited by 47
  9. 2019Effective Cross-lingual Transfer of Neural Machine Translation Models without Shared Vocabulariescited by 27
  10. 2016Neural Machine Translation with Pivot Languagescited by 25
  11. 2016Towards cross-lingual distributed representations without parallel text trained with adversarial autoencoderscited by 13
  12. 2019A Universal Parent Model for Low-Resource Neural Machine Translation Transfercited by 10
  13. 2019Improving Unsupervised Word-by-Word Translation with Language Model and Denoising Autoencodercited by 5

Built on by

Cited by year

Citing papers per year: 2022: 2; 2023: 0; 2024: 0; 2025: 1.

3 papers.

  1. 2022The first neural machine translation system for the Erzya languagecited by 7
  2. 2022ConsistTL: Modeling Consistency in Transfer Learning for Low-Resource Neural Machine Translationcited by 4
  3. 2025The first open machine translation system for the Chechen languagecited by 0