Cognate Projection for Low-Resource Inflection Generation
Bradley Hauer, Amir Ahmad Habibi, Yixing Luan, Rashed Rubby Riyadh, Grzegorz Kondrak
Abstract
We propose cognate projection as a method of crosslingual transfer for inflection generation in the context of the SIGMORPHON 2019 Shared Task. The results on four language pairs show the method is effective when no low-resource training data is available.- Anthology ID:
- W19-4202
- Volume:
- Proceedings of the 16th Workshop on Computational Research in Phonetics, Phonology, and Morphology
- Month:
- August
- Year:
- 2019
- Address:
- Florence, Italy
- Editors:
- Garrett Nicolai, Ryan Cotterell
- Venue:
- ACL
- SIG:
- SIGMORPHON
- Publisher:
- Association for Computational Linguistics
- Note:
- Pages:
- 6–11
- Language:
- URL:
- https://aclanthology.org/W19-4202
- DOI:
- 10.18653/v1/W19-4202
- Cite (ACL):
- Bradley Hauer, Amir Ahmad Habibi, Yixing Luan, Rashed Rubby Riyadh, and Grzegorz Kondrak. 2019. Cognate Projection for Low-Resource Inflection Generation. In Proceedings of the 16th Workshop on Computational Research in Phonetics, Phonology, and Morphology, pages 6–11, Florence, Italy. Association for Computational Linguistics.
- Cite (Informal):
- Cognate Projection for Low-Resource Inflection Generation (Hauer et al., ACL 2019)
- PDF:
- https://preview.aclanthology.org/ingest-bitext-workshop/W19-4202.pdf