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
Bibkey:
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)
Copy Citation:
PDF:
https://preview.aclanthology.org/emnlp22-frontmatter/2021.sigmorphon-1.7.pdf
Video:
 https://preview.aclanthology.org/emnlp22-frontmatter/2021.sigmorphon-1.7.mp4
Code
 saujasv/phonological-generalizations