Decomposing Fusional Morphemes with Vector Embeddings

Michael Ginn, Alexis Palmer


Abstract
Distributional approaches have proven effective in modeling semantics and phonology through vector embeddings. We explore whether distributional representations can also effectively model morphological information. We train static vector embeddings over morphological sequences. Then, we explore morpheme categories for fusional morphemes, which encode multiple linguistic dimensions, and often have close relationships to other morphemes. We study whether the learned vector embeddings align with these linguistic dimensions, finding strong evidence that this is the case. Our work uses two low-resource languages, Uspanteko and Tsez, demonstrating that distributional morphological representations are effective even with limited data.
Anthology ID:
2024.sigmorphon-1.7
Volume:
Proceedings of the 21st SIGMORPHON workshop on Computational Research in Phonetics, Phonology, and Morphology
Month:
June
Year:
2024
Address:
Mexico City, Mexico
Editors:
Garrett Nicolai, Eleanor Chodroff, Frederic Mailhot, Çağrı Çöltekin
Venue:
SIGMORPHON
SIG:
SIGMORPHON
Publisher:
Association for Computational Linguistics
Note:
Pages:
57–66
Language:
URL:
https://aclanthology.org/2024.sigmorphon-1.7
DOI:
10.18653/v1/2024.sigmorphon-1.7
Bibkey:
Cite (ACL):
Michael Ginn and Alexis Palmer. 2024. Decomposing Fusional Morphemes with Vector Embeddings. In Proceedings of the 21st SIGMORPHON workshop on Computational Research in Phonetics, Phonology, and Morphology, pages 57–66, Mexico City, Mexico. Association for Computational Linguistics.
Cite (Informal):
Decomposing Fusional Morphemes with Vector Embeddings (Ginn & Palmer, SIGMORPHON 2024)
Copy Citation:
PDF:
https://aclanthology.org/2024.sigmorphon-1.7.pdf