Abstract
Morphological rules with various levels of specificity can be learned from example lexemes by recursive application of minimal generalization (Albright and Hayes, 2002, 2003). A model that learns rules solely through minimal generalization was used to predict average human wug-test ratings from German, English, and Dutch in the SIGMORPHON-UniMorph 2021 Shared Task, with competitive results. Some formal properties of the minimal generalization operation were proved. An automatic method was developed to create wug-test stimuli for future experiments that investigate whether the model’s morphological generalizations are too minimal.- Anthology ID:
- 2021.sigmorphon-1.29
- Volume:
- Proceedings of the 18th SIGMORPHON Workshop on Computational Research in Phonetics, Phonology, and Morphology
- Month:
- August
- Year:
- 2021
- Address:
- Online
- Venue:
- SIGMORPHON
- SIG:
- SIGMORPHON
- Publisher:
- Association for Computational Linguistics
- Note:
- Pages:
- 283–291
- Language:
- URL:
- https://aclanthology.org/2021.sigmorphon-1.29
- DOI:
- 10.18653/v1/2021.sigmorphon-1.29
- Cite (ACL):
- Colin Wilson and Jane S.Y. Li. 2021. Were We There Already? Applying Minimal Generalization to the SIGMORPHON-UniMorph Shared Task on Cognitively Plausible Morphological Inflection. In Proceedings of the 18th SIGMORPHON Workshop on Computational Research in Phonetics, Phonology, and Morphology, pages 283–291, Online. Association for Computational Linguistics.
- Cite (Informal):
- Were We There Already? Applying Minimal Generalization to the SIGMORPHON-UniMorph Shared Task on Cognitively Plausible Morphological Inflection (Wilson & Li, SIGMORPHON 2021)
- PDF:
- https://preview.aclanthology.org/remove-xml-comments/2021.sigmorphon-1.29.pdf