Abstract
This paper reports system descriptions for FJWU-NRPU team for participation in the WMT20 Biomedical shared translation task. We focused our submission on exploring the effects of adding in-domain corpora extracted from various out-of-domain sources. Systems were built for French to English using in-domain corpora through fine tuning and selective data training. We further explored BERT based models specifically with focus on effect of domain adaptive subword units.- Anthology ID:
- 2020.wmt-1.92
- 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:
- 849–856
- Language:
- URL:
- https://aclanthology.org/2020.wmt-1.92
- DOI:
- Cite (ACL):
- Sumbal Naz, Sadaf Abdul Rauf, Noor-e- Hira, and Sami Ul Haq. 2020. FJWU participation for the WMT20 Biomedical Translation Task. In Proceedings of the Fifth Conference on Machine Translation, pages 849–856, Online. Association for Computational Linguistics.
- Cite (Informal):
- FJWU participation for the WMT20 Biomedical Translation Task (Naz et al., WMT 2020)
- PDF:
- https://preview.aclanthology.org/nodalida-main-page/2020.wmt-1.92.pdf