mlsanityData to 7 Oct 2026

Unsupervised Machine Translation On Dravidian Languages

arXiv 2103.15877 ↗First posted 29 Mar 2021cs.CL cs.AIcited by 4

Not on the map. Why?

Abstract (arXiv)

Unsupervised neural machine translation (UNMT) is beneficial especially for low resource languages such as those from the Dravidian family. However, UNMT systems tend to fail in realistic scenarios involving actual low resource languages. Recent works propose to utilize auxiliary parallel data and have achieved state-of-the-art results. In this work, we focus on unsupervised translation between English and Kannada, a low resource Dravidian language. We additionally utilize a limited amount of auxiliary data between English and other related Dravidian languages. We show that unifying the writing systems is essential in unsupervised translation between the Dravidian languages. We explore several model architectures that use the auxiliary data in order to maximize knowledge sharing and enable UNMT for distant language pairs. Our experiments demonstrate that it is crucial to include auxiliary languages that are similar to our focal language, Kannada. Furthermore, we propose a metric to measure language similarity and show that it serves as a good indicator for selecting the auxiliary languages.

Key facts. Cited by 4 papers in the map (data through 7 Oct 2026). Builds on 19 of its 32 references that are in the map. First posted on arXiv 29 Mar 2021.

Builds on

19 of 32 references.

References · 19

  1. 2017Attention Is All You Needcited by 59,932
  2. 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,204
  3. 2014Neural Machine Translation by Jointly Learning to Align and Translatecited by 4,530
  4. 2015Neural Machine Translation of Rare Words with Subword Unitscited by 2,898
  5. 2018A Call for Clarity in Reporting BLEU Scorescited by 1,790
  6. 2019Cross-lingual Language Model Pretrainingcited by 1,088
  7. 2020Multilingual Denoising Pre-training for Neural Machine Translationcited by 1,028
  8. 2017Six Challenges for Neural Machine Translationcited by 334
  9. 2017Unsupervised Machine Translation Using Monolingual Corpora Onlycited by 272
  10. 2017Unsupervised Neural Machine Translationcited by 148
  11. 2019The FLoRes Evaluation Datasets for Low-Resource Machine Translation: Nepali-English and Sinhala-Englishcited by 61
  12. 2020AI4Bharat-IndicNLP Corpus: Monolingual Corpora and Word Embeddings for Indic Languagescited by 43
7 more
  1. 2020PMIndia -- A Collection of Parallel Corpora of Languages of Indiacited by 40
  2. 2020When Does Unsupervised Machine Translation Work?cited by 38
  3. 2020When and Why is Unsupervised Neural Machine Translation Useless?cited by 34
  4. 2020A Multilingual View of Unsupervised Machine Translationcited by 23
  5. 2020Harnessing Multilinguality in Unsupervised Machine Translation for Rare Languagescited by 22
  6. 2020Reference Language based Unsupervised Neural Machine Translationcited by 12
  7. 2020SJTU-NICT's Supervised and Unsupervised Neural Machine Translation Systems for the WMT20 News Translation Taskcited by 4

Built on by

Cited by year

Citing papers per year: 2021: 3; 2022: 1.

4 papers.

  1. 2021The FLORES-101 Evaluation Benchmark for Low-Resource and Multilingual Machine Translationcited by 556
  2. 2021Alternative Input Signals Ease Transfer in Multilingual Machine Translationcited by 14
  3. 2021Integrating Unsupervised Data Generation into Self-Supervised Neural Machine Translation for Low-Resource Languagescited by 4
  4. 2022Cost-Effective Training in Low-Resource Neural Machine Translationcited by 2