SOTAVerified

Word-level Morpheme segmentation using Transformer neural network

2022-07-01NAACL (SIGMORPHON) 2022Unverified0· sign in to hype

Tsolmon Zundi, Chinbat Avaajargal

Unverified — Be the first to reproduce this paper.

Reproduce

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.

Tasks

Reproductions