A Neural Model for Regular Grammar Induction

TL;DR

This paper introduces a neural model for inducing regular grammars from data, which is fully explainable, interpretable, and capable of learning various regular grammars with high accuracy.

Contribution

It presents a novel neural approach to regular grammar induction that is explainable, interpretable, and effective across diverse test scenarios.

Findings

Achieves high recall and precision in grammar induction

Model's intermediate results are directly interpretable as partial parses

Capable of learning arbitrary regular grammars with sufficient data

Abstract

Grammatical inference is a classical problem in computational learning theory and a topic of wider influence in natural language processing. We treat grammars as a model of computation and propose a novel neural approach to induction of regular grammars from positive and negative examples. Our model is fully explainable, its intermediate results are directly interpretable as partial parses, and it can be used to learn arbitrary regular grammars when provided with sufficient data. We find that our method consistently attains high recall and precision scores across a range of tests of varying complexity.