A Neural Model for Regular Grammar Induction
This addresses grammatical inference for natural language processing, offering an incremental improvement with explainable neural methods.
The authors tackled the problem of inducing regular grammars from examples by proposing a novel neural approach that is fully explainable and interpretable, achieving high recall and precision scores across various complexity tests.
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.