conftrace_
2022 NAACL NAACL 2022

Word-level Morpheme segmentation using Transformer neural network

Abstract

AbstractThis 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.

🧭 Keyword Pioneer — word-level segmentation
🐝 Cross-Pollinator — Artificial Intelligence, Computer Science, Computer Vision, Deep Learning, Interdisciplinary, Knowledge & Reasoning, Machine Learning, Mathematics & Optimization, Natural Language Processing, Reinforcement Learning, Speech & Audio