mlsanityData to 14 Oct 2026

Machine Translation into Low-resource Language Varieties

arXiv 2106.06797 ↗First posted 12 Jun 2021cs.CLcited by 19

Not on the map. Why?

Abstract (arXiv)

State-of-the-art machine translation (MT) systems are typically trained to generate the "standard" target language; however, many languages have multiple varieties (regional varieties, dialects, sociolects, non-native varieties) that are different from the standard language. Such varieties are often low-resource, and hence do not benefit from contemporary NLP solutions, MT included. We propose a general framework to rapidly adapt MT systems to generate language varieties that are close to, but different from, the standard target language, using no parallel (source--variety) data. This also includes adaptation of MT systems to low-resource typologically-related target languages. We experiment with adapting an English--Russian MT system to generate Ukrainian and Belarusian, an English--Norwegian Bokmaal system to generate Nynorsk, and an English--Arabic system to generate four Arabic dialects, obtaining significant improvements over competitive baselines.

Key facts. Cited by 19 papers in the map (data through 14 Oct 2026). Builds on 31 of its 55 references that are in the map. First posted on arXiv 12 Jun 2021.

Builds on

31 of 55 references.

References · 31

  1. 2017Attention Is All You Needcited by 60,361
  2. 2019BERTScore: Evaluating Text Generation with BERTcited by 5,512
  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. 2018A Call for Clarity in Reporting BLEU Scorescited by 1,799
  6. 2016Enriching Word Vectors with Subword Informationcited by 1,583
  7. 2020BLEURT: Learning Robust Metrics for Text Generationcited by 1,203
  8. 2019Cross-lingual Language Model Pretrainingcited by 1,090
  9. 2019On the Variance of the Adaptive Learning Rate and Beyondcited by 772
  10. 2020Stanza: A Python Natural Language Processing Toolkit for Many Human Languagescited by 723
  11. 2020Making Monolingual Sentence Embeddings Multilingual using Knowledge Distillationcited by 593
  12. 2017Word Translation Without Parallel Datacited by 487
19 more
  1. 2017Unsupervised Machine Translation Using Monolingual Corpora Onlycited by 273
  2. 2017OpenNMT: Open-source Toolkit for Neural Machine Translationcited by 251
  3. 2019WikiMatrix: Mining 135M Parallel Sentences in 1620 Language Pairs from Wikipediacited by 223
  4. 2020Tangled up in BLEU: Reevaluating the Evaluation of Automatic Machine Translation Evaluation Metricscited by 158
  5. 2017Unsupervised Neural Machine Translationcited by 149
  6. 2019CCAligned: A Massive Collection of Cross-Lingual Web-Document Pairscited by 136
  7. 2020A Monolingual Approach to Contextualized Word Embeddings for Mid-Resource Languagescited by 131
  8. 2018A Unified Approach to Quantifying Algorithmic Unfairness: Measuring Individual & Group Unfairness via Inequality Indicescited by 97
  9. 2018Unsupervised Text Style Transfer using Language Models as Discriminatorscited by 70
  10. 2020A Probabilistic Formulation of Unsupervised Text Style Transfercited by 70
  11. 2020When Does Unsupervised Machine Translation Work?cited by 38
  12. 2019Domain Adaptation of Neural Machine Translation by Lexicon Inductioncited by 33
  13. 2018Von Mises-Fisher Loss for Training Sequence to Sequence Models with Continuous Outputscited by 27
  14. 2020A Multilingual View of Unsupervised Machine Translationcited by 23
  15. 2020Harnessing Multilinguality in Unsupervised Machine Translation for Rare Languagescited by 22
  16. 2018Adapting Word Embeddings to New Languages with Morphological and Phonological Subword Representationscited by 18
  17. 2020Reusing a Pretrained Language Model on Languages with Limited Corpora for Unsupervised NMTcited by 18
  18. 2018Neural Machine Translation into Language Varietiescited by 9
  19. 2021An Exploration of Data Augmentation Techniques for Improving English to Tigrinya Translationcited by 6

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2021: 4; 2022: 4; 2023: 3; 2024: 5; 2025: 1; 2026: 2.

19 papers.

Sort:

By area:

  1. 2021Survey of Low-Resource Machine Translationcited by 92
  2. 2023The unreasonable effectiveness of few-shot learning for machine translationcited by 91
  3. 2022Language Generation Models Can Cause Harm: So What Can We Do About It? An Actionable Surveycited by 80
  4. 2023GIVT: Generative Infinite-Vocabulary Transformerscited by 80
  5. 2021A Survey of Race, Racism, and Anti-Racism in NLPcited by 75
  6. 2024Natural Language Processing for Dialects of a Language: A Surveycited by 40
  7. 2021Efficient Test Time Adapter Ensembling for Low-resource Language Varietiescited by 26
  8. 2022FRMT: A Benchmark for Few-Shot Region-Aware Machine Translationcited by 18
  9. 2023CODET: A Benchmark for Contrastive Dialectal Evaluation of Machine Translationcited by 9
  10. 2021Towards Universality in Multilingual Text Rewritingcited by 7
  11. 2022Dim Wihl Gat Tun: The Case for Linguistic Expertise in NLP for Underdocumented Languagescited by 2
  12. 2024KpopMT: Translation Dataset with Terminology for Kpop Fandomcited by 2
7 more
  1. 2022High-Resource Methodological Bias in Low-Resource Investigationscited by 1
  2. 2024Dialectal and Low-Resource Machine Translation for Aromaniancited by 1
  3. 2024Birdie: Advancing State Space Models with Reward-Driven Objectives and Curriculacited by 1
  4. 2024Datasets for Multilingual Answer Sentence Selectioncited by 0
  5. 2025Using Contextually Aligned Online Reviews to Measure LLMs' Performance Disparities Across Language Varietiescited by 0
  6. 2026A Komi-Yazva--Russian Parallel Corpus and Evaluation Protocol for Zero- and Few-Shot LLM Translationcited by 0
  7. 2026Machine Translation between English and Syriac (East Syriac Dialect) using Statistical Machine Learningcited by 0