Abstract
Modern work on the cross-linguistic computational modeling of morphological inflection has typically employed language-independent data splitting algorithms. In this paper, we supplement that approach with language-specific probes designed to test aspects of morphological generalization. Testing these probes on three morphologically distinct languages, English, Spanish, and Swahili, we find evidence that three leading morphological inflection systems employ distinct generalization strategies over conjugational classes and feature sets on both orthographic and phonologically transcribed inputs.- Anthology ID:
- 2023.emnlp-main.552
- Volume:
- Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing
- Month:
- December
- Year:
- 2023
- Address:
- Singapore
- Editors:
- Houda Bouamor, Juan Pino, Kalika Bali
- Venue:
- EMNLP
- SIG:
- Publisher:
- Association for Computational Linguistics
- Note:
- Pages:
- 8933–8941
- Language:
- URL:
- https://aclanthology.org/2023.emnlp-main.552
- DOI:
- 10.18653/v1/2023.emnlp-main.552
- Cite (ACL):
- Jordan Kodner, Salam Khalifa, and Sarah Ruth Brogden Payne. 2023. Exploring Linguistic Probes for Morphological Generalization. In Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing, pages 8933–8941, Singapore. Association for Computational Linguistics.
- Cite (Informal):
- Exploring Linguistic Probes for Morphological Generalization (Kodner et al., EMNLP 2023)
- PDF:
- https://preview.aclanthology.org/corrections-2024-05/2023.emnlp-main.552.pdf