Abstract
In this paper, we discuss the details of the various Machine Translation (MT) systems that we have submitted for the English-Marathi LoResMT task. As a part of this task, we have submitted three different Neural Machine Translation (NMT) systems; a Baseline English-Marathi system, a Baseline Marathi-English system, and an English-Marathi system that is based on the back-translation technique. We explore the performance of these NMT systems between English and Marathi languages, which forms a low resource language pair due to unavailability of sufficient parallel data. We also explore the performance of the back-translation technique when the back-translated data is obtained from NMT systems that are trained on a very less amount of data. From our experiments, we observe that the back-translation technique can help improve the MT quality over the baseline for the English-Marathi language pair.- Anthology ID:
- 2021.mtsummit-loresmt.17
- Volume:
- Proceedings of the 4th Workshop on Technologies for MT of Low Resource Languages (LoResMT2021)
- Month:
- August
- Year:
- 2021
- Address:
- Virtual
- Editors:
- John Ortega, Atul Kr. Ojha, Katharina Kann, Chao-Hong Liu
- Venue:
- LoResMT
- SIG:
- Publisher:
- Association for Machine Translation in the Americas
- Note:
- Pages:
- 158–162
- Language:
- URL:
- https://aclanthology.org/2021.mtsummit-loresmt.17
- DOI:
- Cite (ACL):
- Aditya Jain, Shivam Mhaskar, and Pushpak Bhattacharyya. 2021. Evaluating the Performance of Back-translation for Low Resource English-Marathi Language Pair: CFILT-IITBombay @ LoResMT 2021. In Proceedings of the 4th Workshop on Technologies for MT of Low Resource Languages (LoResMT2021), pages 158–162, Virtual. Association for Machine Translation in the Americas.
- Cite (Informal):
- Evaluating the Performance of Back-translation for Low Resource English-Marathi Language Pair: CFILT-IITBombay @ LoResMT 2021 (Jain et al., LoResMT 2021)
- PDF:
- https://preview.aclanthology.org/nschneid-patch-2/2021.mtsummit-loresmt.17.pdf