Sample-efficient Linguistic Generalizations through Program Synthesis: Experiments with Phonology Problems

TL;DR

This paper introduces a program synthesis approach to learn explicit phonology rules from few examples, demonstrating high sample efficiency and interpretability on linguistics problems.

Contribution

We develop a synthesis model that learns human-readable phonology rules as programs, enabling strong generalization from limited data and interpretability.

Findings

High sample efficiency in learning phonology rules

Generated human-readable and controllable programs

Effective generalization on linguistics Olympiad problems

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.