Abstract
In this article, we describe the TALP-UPC participation in the WMT20 news translation shared task for Tamil-English. Given the low amount of parallel training data, we resort to adapt the task to a multilingual system to benefit from the positive transfer from high resource languages. We use iterative backtranslation to fine-tune the system and benefit from the monolingual data available. In order to measure the effectivity of such methods, we compare our results to a bilingual baseline system.- Anthology ID:
- 2020.wmt-1.10
- Volume:
- Proceedings of the Fifth Conference on Machine Translation
- Month:
- November
- Year:
- 2020
- Address:
- Online
- Venue:
- WMT
- SIG:
- SIGMT
- Publisher:
- Association for Computational Linguistics
- Note:
- Pages:
- 134–138
- Language:
- URL:
- https://aclanthology.org/2020.wmt-1.10
- DOI:
- Cite (ACL):
- Carlos Escolano, Marta R. Costa-jussà, and José A. R. Fonollosa. 2020. The TALP-UPC System Description for WMT20 News Translation Task: Multilingual Adaptation for Low Resource MT. In Proceedings of the Fifth Conference on Machine Translation, pages 134–138, Online. Association for Computational Linguistics.
- Cite (Informal):
- The TALP-UPC System Description for WMT20 News Translation Task: Multilingual Adaptation for Low Resource MT (Escolano et al., WMT 2020)
- PDF:
- https://preview.aclanthology.org/ingestion-script-update/2020.wmt-1.10.pdf