Word-level Morpheme segmentation using Transformer neural network
Tsolmon Zundi | Chinbat Avaajargal
Proceedings of the 19th SIGMORPHON Workshop on Computational Research in Phonetics, Phonology, and Morphology
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.