Transfer learning in low-resourced MT: An empirical study
Sainik Kumar Mahata, Dipanjan Saha, Dipankar Das, Sivaji Bandyopadhyay
Abstract
Translation systems rely on a large and goodquality parallel corpus for producing reliable translations. However, obtaining such a corpus for low-resourced languages is a challenge. New research has shown that transfer learning can mitigate this issue by augmenting lowresourced MT systems with high-resourced ones. In this work, we explore two types of transfer learning techniques, namely, crosslingual transfer learning and multilingual training, both with information augmentation, to examine the degree of performance improvement following the augmentation. Furthermore, we use languages of the same family (Romanic, in our case), to investigate the role of the shared linguistic property, in producing dependable translations.- Anthology ID:
- 2023.icon-1.63
- Volume:
- Proceedings of the 20th International Conference on Natural Language Processing (ICON)
- Month:
- December
- Year:
- 2023
- Address:
- Goa University, Goa, India
- Editors:
- Jyoti D. Pawar, Sobha Lalitha Devi
- Venue:
- ICON
- SIG:
- SIGLEX
- Publisher:
- NLP Association of India (NLPAI)
- Note:
- Pages:
- 646–650
- Language:
- URL:
- https://aclanthology.org/2023.icon-1.63
- DOI:
- Cite (ACL):
- Sainik Kumar Mahata, Dipanjan Saha, Dipankar Das, and Sivaji Bandyopadhyay. 2023. Transfer learning in low-resourced MT: An empirical study. In Proceedings of the 20th International Conference on Natural Language Processing (ICON), pages 646–650, Goa University, Goa, India. NLP Association of India (NLPAI).
- Cite (Informal):
- Transfer learning in low-resourced MT: An empirical study (Mahata et al., ICON 2023)
- PDF:
- https://preview.aclanthology.org/ml4al-ingestion/2023.icon-1.63.pdf