Sample-efficient Linguistic Generalizations through Program Synthesis: Experiments with Phonology Problems
This addresses the challenge of sample-efficient linguistic generalization for tasks requiring strong reasoning, though it is incremental in applying program synthesis to a specific domain.
The paper tackled the problem of learning explicit linguistic rules from few examples using program synthesis, achieving high sample efficiency and generating human-readable programs on a dataset of Linguistics Olympiad problems.
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.