Learning Phonotactics from Linguistic Informants

TL;DR

This paper introduces an interactive model that learns phonotactic rules by querying a linguistic informant, demonstrating high sample efficiency in both natural and generated languages.

Contribution

It presents a novel interactive learning framework that uses information-theoretic policies to efficiently learn phonotactic constraints from linguistic informants.

Findings

Achieves comparable or better sample efficiency than fully supervised methods.

Effective in both natural and procedurally-generated languages.

Demonstrates the utility of interactive, informant-based learning for phonotactics.

Abstract

We propose an interactive approach to language learning that utilizes linguistic acceptability judgments from an informant (a competent language user) to learn a grammar. Given a grammar formalism and a framework for synthesizing data, our model iteratively selects or synthesizes a data-point according to one of a range of information-theoretic policies, asks the informant for a binary judgment, and updates its own parameters in preparation for the next query. We demonstrate the effectiveness of our model in the domain of phonotactics, the rules governing what kinds of sound-sequences are acceptable in a language, and carry out two experiments, one with typologically-natural linguistic data and another with a range of procedurally-generated languages. We find that the information-theoretic policies that our model uses to select items to query the informant achieve sample efficiency comparable to, and sometimes greater than, fully supervised approaches.