Machine Translation for English–Inuktitut with Segmentation, Data Acquisition and Pre-Training
Christian Roest, Lukas Edman, Gosse Minnema, Kevin Kelly, Jennifer Spenader, Antonio Toral
Abstract
Translating to and from low-resource polysynthetic languages present numerous challenges for NMT. We present the results of our systems for the English–Inuktitut language pair for the WMT 2020 translation tasks. We investigated the importance of correct morphological segmentation, whether or not adding data from a related language (Greenlandic) helps, and whether using contextual word embeddings improves translation. While each method showed some promise, the results are mixed.- Anthology ID:
- 2020.wmt-1.29
- 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:
- 274–281
- Language:
- URL:
- https://aclanthology.org/2020.wmt-1.29
- DOI:
- Cite (ACL):
- Christian Roest, Lukas Edman, Gosse Minnema, Kevin Kelly, Jennifer Spenader, and Antonio Toral. 2020. Machine Translation for English–Inuktitut with Segmentation, Data Acquisition and Pre-Training. In Proceedings of the Fifth Conference on Machine Translation, pages 274–281, Online. Association for Computational Linguistics.
- Cite (Informal):
- Machine Translation for English–Inuktitut with Segmentation, Data Acquisition and Pre-Training (Roest et al., WMT 2020)
- PDF:
- https://preview.aclanthology.org/remove-xml-comments/2020.wmt-1.29.pdf