The ADAPT System Description for the WMT20 News Translation Task
Venkatesh Parthasarathy, Akshai Ramesh, Rejwanul Haque, Andy Way
Abstract
This paper describes the ADAPT Centre’s submissions to the WMT20 News translation shared task for English-to-Tamil and Tamil-to-English. We present our machine translation (MT) systems that were built using the state-of-the-art neural MT (NMT) model, Transformer. We applied various strategies in order to improve our baseline MT systems, e.g. onolin- gual sentence selection for creating synthetic training data, mining monolingual sentences for adapting our MT systems to the task, hyperparameters search for Transformer in lowresource scenarios. Our experiments show that adding the aforementioned techniques to the baseline yields an excellent performance in the English-to-Tamil and Tamil-to-English translation tasks.- Anthology ID:
- 2020.wmt-1.27
- 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:
- 262–268
- Language:
- URL:
- https://aclanthology.org/2020.wmt-1.27
- DOI:
- Cite (ACL):
- Venkatesh Parthasarathy, Akshai Ramesh, Rejwanul Haque, and Andy Way. 2020. The ADAPT System Description for the WMT20 News Translation Task. In Proceedings of the Fifth Conference on Machine Translation, pages 262–268, Online. Association for Computational Linguistics.
- Cite (Informal):
- The ADAPT System Description for the WMT20 News Translation Task (Parthasarathy et al., WMT 2020)
- PDF:
- https://preview.aclanthology.org/ingestion-script-update/2020.wmt-1.27.pdf
- Data
- WikiMatrix