Abstract
This paper presents the submission of team NUM DI to the SIGMORPHON 2022 Task on Morpheme Segmentation Part 1, word-level morpheme segmentation. We explore the transformer neural network approach to the shared task. We develop monolingual models for world-level morpheme segmentation and focus on improving the model by using various training strategies to improve accuracy and generalization across languages.- Anthology ID:
- 2022.sigmorphon-1.15
- Volume:
- Proceedings of the 19th SIGMORPHON Workshop on Computational Research in Phonetics, Phonology, and Morphology
- Month:
- July
- Year:
- 2022
- Address:
- Seattle, Washington
- Editors:
- Garrett Nicolai, Eleanor Chodroff
- Venue:
- SIGMORPHON
- SIG:
- SIGMORPHON
- Publisher:
- Association for Computational Linguistics
- Note:
- Pages:
- 139–143
- Language:
- URL:
- https://aclanthology.org/2022.sigmorphon-1.15
- DOI:
- 10.18653/v1/2022.sigmorphon-1.15
- Cite (ACL):
- Tsolmon Zundi and Chinbat Avaajargal. 2022. Word-level Morpheme segmentation using Transformer neural network. In Proceedings of the 19th SIGMORPHON Workshop on Computational Research in Phonetics, Phonology, and Morphology, pages 139–143, Seattle, Washington. Association for Computational Linguistics.
- Cite (Informal):
- Word-level Morpheme segmentation using Transformer neural network (Zundi & Avaajargal, SIGMORPHON 2022)
- PDF:
- https://preview.aclanthology.org/improve-issue-templates/2022.sigmorphon-1.15.pdf