Sample-efficient Linguistic Generalizations through Program Synthesis: Experiments with Phonology Problems
Saujas Vaduguru, Aalok Sathe, Monojit Choudhury, Dipti Sharma
Abstract
Neural models excel at extracting statistical patterns from large amounts of data, but struggle to learn patterns or reason about language from only a few examples. In this paper, we ask: Can we learn explicit rules that generalize well from only a few examples? We explore this question using program synthesis. We develop a synthesis model to learn phonology rules as programs in a domain-specific language. We test the ability of our models to generalize from few training examples using our new dataset of problems from the Linguistics Olympiad, a challenging set of tasks that require strong linguistic reasoning ability. In addition to being highly sample-efficient, our approach generates human-readable programs, and allows control over the generalizability of the learnt programs.- Anthology ID:
- 2021.sigmorphon-1.7
- Volume:
- Proceedings of the 18th SIGMORPHON Workshop on Computational Research in Phonetics, Phonology, and Morphology
- Month:
- August
- Year:
- 2021
- Address:
- Online
- Editors:
- Garrett Nicolai, Kyle Gorman, Ryan Cotterell
- Venue:
- SIGMORPHON
- SIG:
- SIGMORPHON
- Publisher:
- Association for Computational Linguistics
- Note:
- Pages:
- 60–71
- Language:
- URL:
- https://aclanthology.org/2021.sigmorphon-1.7
- DOI:
- 10.18653/v1/2021.sigmorphon-1.7
- Cite (ACL):
- Saujas Vaduguru, Aalok Sathe, Monojit Choudhury, and Dipti Sharma. 2021. Sample-efficient Linguistic Generalizations through Program Synthesis: Experiments with Phonology Problems. In Proceedings of the 18th SIGMORPHON Workshop on Computational Research in Phonetics, Phonology, and Morphology, pages 60–71, Online. Association for Computational Linguistics.
- Cite (Informal):
- Sample-efficient Linguistic Generalizations through Program Synthesis: Experiments with Phonology Problems (Vaduguru et al., SIGMORPHON 2021)
- PDF:
- https://preview.aclanthology.org/emnlp22-frontmatter/2021.sigmorphon-1.7.pdf
- Code
- saujasv/phonological-generalizations