A Neural Model for Regular Grammar Induction

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...

Full description

Saved in:
Bibliographic Details
Main Authors Belcák, Peter, Hofer, David, Wattenhofer, Roger
Format Journal Article
LanguageEnglish
Published 23.09.2022
Subjects
Computer Science - Computation and Language
Computer Science - Learning
Online AccessGet full text
DOI10.48550/arxiv.2209.11628

Cover

More Information
Summary: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.
DOI:10.48550/arxiv.2209.11628