Abstract
Generalization to novel forms and feature combinations is the key to efficient learning. Recently, Goldman et al. (2022) demonstrated that contemporary neural approaches to morphological inflection still struggle to generalize to unseen words and feature combinations, even in agglutinative languages. In this paper, we argue that the use of morphological segmentation in inflection modeling allows decomposing the problem into sub-problems of substantially smaller search space. We suggest that morphological segments may be globally topologically sorted according to their grammatical categories within a given language. Our experiments demonstrate that such segmentation provides all the necessary information for better generalization, especially in agglutinative languages.- Anthology ID:
- 2023.sigtyp-1.12
- Volume:
- Proceedings of the 5th Workshop on Research in Computational Linguistic Typology and Multilingual NLP
- Month:
- May
- Year:
- 2023
- Address:
- Dubrovnik, Croatia
- Editors:
- Lisa Beinborn, Koustava Goswami, Saliha Muradoğlu, Alexey Sorokin, Ritesh Kumar, Andreas Shcherbakov, Edoardo M. Ponti, Ryan Cotterell, Ekaterina Vylomova
- Venue:
- SIGTYP
- SIG:
- Publisher:
- Association for Computational Linguistics
- Note:
- Pages:
- 120–125
- Language:
- URL:
- https://aclanthology.org/2023.sigtyp-1.12
- DOI:
- 10.18653/v1/2023.sigtyp-1.12
- Cite (ACL):
- Andreas Shcherbakov and Ekaterina Vylomova. 2023. Does Topological Ordering of Morphological Segments Reduce Morphological Modeling Complexity? A Preliminary Study on 13 Languages. In Proceedings of the 5th Workshop on Research in Computational Linguistic Typology and Multilingual NLP, pages 120–125, Dubrovnik, Croatia. Association for Computational Linguistics.
- Cite (Informal):
- Does Topological Ordering of Morphological Segments Reduce Morphological Modeling Complexity? A Preliminary Study on 13 Languages (Shcherbakov & Vylomova, SIGTYP 2023)
- PDF:
- https://preview.aclanthology.org/nschneid-patch-5/2023.sigtyp-1.12.pdf