mlsanityData to 7 Oct 2026

Geographical Distance Is The New Hyperparameter: A Case Study Of Finding The Optimal Pre-trained Language For English-isiZulu Machine Translation

arXiv 2205.08621 ↗First posted 17 May 2022cs.CL cs.AIcited by 5

Not on the map. Why?

Abstract (arXiv)

Stemming from the limited availability of datasets and textual resources for low-resource languages such as isiZulu, there is a significant need to be able to harness knowledge from pre-trained models to improve low resource machine translation. Moreover, a lack of techniques to handle the complexities of morphologically rich languages has compounded the unequal development of translation models, with many widely spoken African languages being left behind. This study explores the potential benefits of transfer learning in an English-isiZulu translation framework. The results indicate the value of transfer learning from closely related languages to enhance the performance of low-resource translation models, thus providing a key strategy for low-resource translation going forward. We gathered results from 8 different language corpora, including one multi-lingual corpus, and saw that isiXhosa-isiZulu outperformed all languages, with a BLEU score of 8.56 on the test set which was better from the multi-lingual corpora pre-trained model by 2.73. We also derived a new coefficient, Nasir's Geographical Distance Coefficient (NGDC) which provides an easy selection of languages for the pre-trained models. NGDC also indicated that isiXhosa should be selected as the language for the pre-trained model.

Key facts. Cited by 5 papers in the map (data through 7 Oct 2026). Builds on 16 of its 29 references that are in the map. First posted on arXiv 17 May 2022.

Builds on

16 of 29 references.

References · 16

  1. 2015Improving Neural Machine Translation Models with Monolingual Datacited by 784
  2. 2017Six Challenges for Neural Machine Translationcited by 334
  3. 2018Marian: Fast Neural Machine Translation in C++cited by 202
  4. 2016Transfer Learning for Low-Resource Neural Machine Translationcited by 188
  5. 2019Choosing Transfer Languages for Cross-Lingual Learningcited by 143
  6. 2021Survey of Low-Resource Machine Translationcited by 92
  7. 2018Rapid Adaptation of Neural Machine Translation to New Languagescited by 82
  8. 2019Tagged Back-Translationcited by 76
  9. 2019Revisiting Low-Resource Neural Machine Translation: A Case Studycited by 61
  10. 2017Transfer Learning across Low-Resource, Related Languages for Neural Machine Translationcited by 58
  11. 2019On The Evaluation of Machine Translation Systems Trained With Back-Translationcited by 40
  12. 2020Dynamic Data Selection and Weighting for Iterative Back-Translationcited by 25
4 more
  1. 2019A Focus on Neural Machine Translation for African Languagescited by 15
  2. 2020Low Resource Neural Machine Translation: A Benchmark for Five African Languagescited by 15
  3. 2021Canonical and Surface Morphological Segmentation for Nguni Languagescited by 10
  4. 2021Low-Resource Neural Machine Translation for Southern African Languagescited by 7

Built on by

Cited by year

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

5 papers.

  1. 2023LLMatic: Neural Architecture Search via Large Language Models and Quality Diversity Optimizationcited by 86
  2. 2023NLNDE at SemEval-2023 Task 12: Adaptive Pretraining and Source Language Selection for Low-Resource Multilingual Sentiment Analysiscited by 10
  3. 2024Pre-Trained Language Models Represent Some Geographic Populations Better Than Otherscited by 6
  4. 2022Enriching Biomedical Knowledge for Low-resource Language Through Large-Scale Translationcited by 4
  5. 2022MTet: Multi-domain Translation for English and Vietnamesecited by 4