English-Marathi Neural Machine Translation Using Local Attention

Reddy, K. Adi Narayana; Prasad, G. Shyam Chandra; Reddy, A. Rajashekar; Kumar, Lalan; Kannaiah,

doi:10.1007/978-981-16-0401-0_21

Cited by 2 publications

(1 citation statement)

References 12 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…(Jadhav, 2020b;Puranik et al, 2021) developed a machine translation system for Marathi to English using transformers on a parallel corpus. Other works on improving machine translation include (Adi Narayana Reddy et al, 2021) proposing an English-Marathi NMT using local attention. The same can be stated to Irish, as it is a poorly resourced language, as the quality of the MT outputs have struggled to achieve the same level as well-supported languages (Dowling et al, 2016;Rehm and Uszkoreit, 2012).…”

Section: Related Workmentioning

confidence: 99%

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

Puranik¹,

Hande²,

Priyadharshini³

et al. 2021

Preprint

View full text Add to dashboard Cite

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. The codes for our systems are published 1 .

show abstract

Section: Related Workmentioning

confidence: 99%