mlsanityData to 7 Oct 2026

Attentive fine-tuning of Transformers for Translation of low-resourced languages @LoResMT 2021

arXiv 2108.08556 ↗First posted 19 Aug 2021cs.CLcited by 4

Not on the map. Why?

Abstract (arXiv)

This paper reports the Machine Translation (MT) systems submitted by the IIITT team for the English->Marathi and English->Irish language pairs LoResMT 2021 shared task. The task focuses on getting exceptional translations for rather low-resourced languages like Irish and Marathi. We fine-tune IndicTrans, a pretrained multilingual NMT model for English->Marathi, using external parallel corpus as input for additional training. We have used a pretrained Helsinki-NLP Opus MT English->Irish model for the latter language pair. Our approaches yield relatively promising results on the BLEU metrics. Under the team name IIITT, our systems ranked 1, 1, and 2 in English->Marathi, Irish->English, and English->Irish, respectively.

Key facts. Cited by 4 papers in the map (data through 7 Oct 2026). Builds on 23 of its 58 references that are in the map. First posted on arXiv 19 Aug 2021.

Builds on

23 of 58 references.

References · 23

  1. 2017Attention Is All You Needcited by 59,932
  2. 2014Neural Machine Translation by Jointly Learning to Align and Translatecited by 4,530
  3. 2014Sequence to Sequence Learning with Neural Networkscited by 2,974
  4. 2019fairseq: A Fast, Extensible Toolkit for Sequence Modelingcited by 1,486
  5. 2017Mixed Precision Trainingcited by 1,135
  6. 2020Language-agnostic BERT Sentence Embeddingcited by 621
  7. 2020Beyond English-Centric Multilingual Machine Translationcited by 559
  8. 2016Google's Multilingual Neural Machine Translation System: Enabling Zero-Shot Translationcited by 467
  9. 2019Massively Multilingual Neural Machine Translationcited by 246
  10. 2021Samanantar: The Largest Publicly Available Parallel Corpora Collection for 11 Indic Languagescited by 133
  11. 2020The Tatoeba Translation Challenge -- Realistic Data Sets for Low Resource and Multilingual MTcited by 127
  12. 2016Toward Multilingual Neural Machine Translation with Universal Encoder and Decodercited by 76
11 more
  1. 2016Multi-Source Neural Translationcited by 37
  2. 2016Semi-Supervised Learning for Neural Machine Translationcited by 36
  3. 2018Multilingual NMT with a language-independent attention bridgecited by 20
  4. 2018Investigating Backtranslation in Neural Machine Translationcited by 14
  5. 2020Revisiting Low Resource Status of Indian Languages in Machine Translationcited by 12
  6. 2019Exploiting Out-of-Domain Parallel Data through Multilingual Transfer Learning for Low-Resource Neural Machine Translationcited by 11
  7. 2021Findings of the LoResMT 2021 Shared Task on COVID and Sign Language for Low-resource Languagescited by 10
  8. 2021IIITT@LT-EDI-EACL2021-Hope Speech Detection: There is always Hope in Transformerscited by 6
  9. 2020A Survey of Orthographic Information in Machine Translationcited by 5
  10. 2021UVCE-IIITT@DravidianLangTech-EACL2021: Tamil Troll Meme Classification: You need to Pay more Attentioncited by 5
  11. 2020Marathi To English Neural Machine Translation With Near Perfect Corpus And Transformerscited by 2

Built on by

Cited by year

Citing papers per year: 2021: 2; 2022: 0; 2023: 0; 2024: 2.

4 papers.

  1. 2024gaHealth: An English-Irish Bilingual Corpus of Health Datacited by 3
  2. 2024adaptNMT: an open-source, language-agnostic development environment for Neural Machine Translationcited by 2
  3. 2021IIITT@Dravidian-CodeMix-FIRE2021: Transliterate or translate? Sentiment analysis of code-mixed text in Dravidian languagescited by 1
  4. 2021Pegasus@Dravidian-CodeMix-HASOC2021: Analyzing Social Media Content for Detection of Offensive Textcited by 0