JB132 submission to the SIGMORPHON 2022 Shared Task 3 on Morphological Segmentation

Jan Bodnár


Abstract
This paper describes the JB132 submission to the SIGMORPHON 2022 Shared Task 3 on Morpheme Segmentation. In this paper we describe probabilistic model trained with the Expectation-Maximization algorithm, we provide the results and analyze sources of errors and general limitations of our approach. The model was implemented within our own modular probabilistic framework.
Anthology ID:
2022.sigmorphon-1.17
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:
152–156
Language:
URL:
https://aclanthology.org/2022.sigmorphon-1.17
DOI:
10.18653/v1/2022.sigmorphon-1.17
Bibkey:
Cite (ACL):
Jan Bodnár. 2022. JB132 submission to the SIGMORPHON 2022 Shared Task 3 on Morphological Segmentation. In Proceedings of the 19th SIGMORPHON Workshop on Computational Research in Phonetics, Phonology, and Morphology, pages 152–156, Seattle, Washington. Association for Computational Linguistics.
Cite (Informal):
JB132 submission to the SIGMORPHON 2022 Shared Task 3 on Morphological Segmentation (Bodnár, SIGMORPHON 2022)
Copy Citation:
PDF:
https://aclanthology.org/2022.sigmorphon-1.17.pdf
Data
UniMorph 4.0