Neural Machine Translation in Low-Resource Setting: a Case Study in English-Marathi Pair

Aakash Banerjee, Aditya Jain, Shivam Mhaskar, Sourabh Dattatray Deoghare, Aman Sehgal, Pushpak Bhattacharya


Abstract
In this paper and we explore different techniques of overcoming the challenges of low-resource in Neural Machine Translation (NMT) and specifically focusing on the case of English-Marathi NMT. NMT systems require a large amount of parallel corpora to obtain good quality translations. We try to mitigate the low-resource problem by augmenting parallel corpora or by using transfer learning. Techniques such as Phrase Table Injection (PTI) and back-translation and mixing of language corpora are used for enhancing the parallel data; whereas pivoting and multilingual embeddings are used to leverage transfer learning. For pivoting and Hindi comes in as assisting language for English-Marathi translation. Compared to baseline transformer model and a significant improvement trend in BLEU score is observed across various techniques. We have done extensive manual and automatic and qualitative evaluation of our systems. Since the trend in Machine Translation (MT) today is post-editing and measuring of Human Effort Reduction (HER) and we have given our preliminary observations on Translation Edit Rate (TER) vs. BLEU score study and where TER is regarded as a measure of HER.
Anthology ID:
2021.mtsummit-research.4
Volume:
Proceedings of Machine Translation Summit XVIII: Research Track
Month:
August
Year:
2021
Address:
Virtual
Editors:
Kevin Duh, Francisco Guzmán
Venue:
MTSummit
SIG:
Publisher:
Association for Machine Translation in the Americas
Note:
Pages:
35–47
Language:
URL:
https://aclanthology.org/2021.mtsummit-research.4
DOI:
Bibkey:
Cite (ACL):
Aakash Banerjee, Aditya Jain, Shivam Mhaskar, Sourabh Dattatray Deoghare, Aman Sehgal, and Pushpak Bhattacharya. 2021. Neural Machine Translation in Low-Resource Setting: a Case Study in English-Marathi Pair. In Proceedings of Machine Translation Summit XVIII: Research Track, pages 35–47, Virtual. Association for Machine Translation in the Americas.
Cite (Informal):
Neural Machine Translation in Low-Resource Setting: a Case Study in English-Marathi Pair (Banerjee et al., MTSummit 2021)
Copy Citation:
PDF:
https://aclanthology.org/2021.mtsummit-research.4.pdf
Data
PMIndia