Abstract
This article describes the Aalto University entry to the WMT18 News Translation Shared Task. We participate in the multilingual subtrack with a system trained under the constrained condition to translate from English to both Finnish and Estonian. The system is based on the Transformer model. We focus on improving the consistency of morphological segmentation for words that are similar orthographically, semantically, and distributionally; such words include etymological cognates, loan words, and proper names. For this, we introduce Cognate Morfessor, a multilingual variant of the Morfessor method. We show that our approach improves the translation quality particularly for Estonian, which has less resources for training the translation model.- Anthology ID:
- W18-6410
- Volume:
- Proceedings of the Third Conference on Machine Translation: Shared Task Papers
- Month:
- October
- Year:
- 2018
- Address:
- Belgium, Brussels
- Venue:
- WMT
- SIG:
- SIGMT
- Publisher:
- Association for Computational Linguistics
- Note:
- Pages:
- 386–393
- Language:
- URL:
- https://aclanthology.org/W18-6410
- DOI:
- 10.18653/v1/W18-6410
- Cite (ACL):
- Stig-Arne Grönroos, Sami Virpioja, and Mikko Kurimo. 2018. Cognate-aware morphological segmentation for multilingual neural translation. In Proceedings of the Third Conference on Machine Translation: Shared Task Papers, pages 386–393, Belgium, Brussels. Association for Computational Linguistics.
- Cite (Informal):
- Cognate-aware morphological segmentation for multilingual neural translation (Grönroos et al., WMT 2018)
- PDF:
- https://preview.aclanthology.org/remove-xml-comments/W18-6410.pdf