Abstract
This paper presents the submission of team GUCLASP to SIGMORPHON 2021 Shared Task on Generalization in Morphological Inflection Generation. We develop a multilingual model for Morphological Inflection and primarily focus on improving the model by using various training strategies to improve accuracy and generalization across languages.- Anthology ID:
- 2021.sigmorphon-1.26
- Volume:
- Proceedings of the 18th SIGMORPHON Workshop on Computational Research in Phonetics, Phonology, and Morphology
- Month:
- August
- Year:
- 2021
- Address:
- Online
- Editors:
- Garrett Nicolai, Kyle Gorman, Ryan Cotterell
- Venue:
- SIGMORPHON
- SIG:
- SIGMORPHON
- Publisher:
- Association for Computational Linguistics
- Note:
- Pages:
- 260–267
- Language:
- URL:
- https://aclanthology.org/2021.sigmorphon-1.26
- DOI:
- 10.18653/v1/2021.sigmorphon-1.26
- Cite (ACL):
- Adam Ek and Jean-Philippe Bernardy. 2021. Training Strategies for Neural Multilingual Morphological Inflection. In Proceedings of the 18th SIGMORPHON Workshop on Computational Research in Phonetics, Phonology, and Morphology, pages 260–267, Online. Association for Computational Linguistics.
- Cite (Informal):
- Training Strategies for Neural Multilingual Morphological Inflection (Ek & Bernardy, SIGMORPHON 2021)
- PDF:
- https://preview.aclanthology.org/nschneid-patch-3/2021.sigmorphon-1.26.pdf