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.
@article{arxiv.2106.06566,
title = {Sample-efficient Linguistic Generalizations through Program Synthesis: Experiments with Phonology Problems},
author = {Saujas Vaduguru and Aalok Sathe and Monojit Choudhury and Dipti Misra Sharma},
journal= {arXiv preprint arXiv:2106.06566},
year = {2021}
}