Sharing Data by Language Family: Data Augmentation for Romance Language Morpheme Segmentation

Lauren Levine


Abstract
This paper presents a basic character level sequence-to-sequence approach to morpheme segmentation for the following Romance languages: French, Italian, and Spanish. We experiment with adding a small set of additional linguistic features, as well as with sharing training data between sister languages for morphological categories with low performance in single language base models. We find that while the additional linguistic features were generally not helpful in this instance, data augmentation between sister languages did help to raise the scores of some individual morphological categories, but did not consistently result in an overall improvement when considering the aggregate of the categories.
Anthology ID:
2022.sigmorphon-1.12
Volume:
Proceedings of the 19th SIGMORPHON Workshop on Computational Research in Phonetics, Phonology, and Morphology
Month:
July
Year:
2022
Address:
Seattle, Washington
Venue:
SIGMORPHON
SIG:
SIGMORPHON
Publisher:
Association for Computational Linguistics
Note:
Pages:
117–123
Language:
URL:
https://aclanthology.org/2022.sigmorphon-1.12
DOI:
10.18653/v1/2022.sigmorphon-1.12
Bibkey:
Cite (ACL):
Lauren Levine. 2022. Sharing Data by Language Family: Data Augmentation for Romance Language Morpheme Segmentation. In Proceedings of the 19th SIGMORPHON Workshop on Computational Research in Phonetics, Phonology, and Morphology, pages 117–123, Seattle, Washington. Association for Computational Linguistics.
Cite (Informal):
Sharing Data by Language Family: Data Augmentation for Romance Language Morpheme Segmentation (Levine, SIGMORPHON 2022)
Copy Citation:
PDF:
https://aclanthology.org/2022.sigmorphon-1.12.pdf