# A Neural Model for Regular Grammar Induction

arXiv: https://arxiv.org/abs/2209.11628 · HTML: https://mlsanity.com/paper/2209.11628/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 4 of its 22 references that are in the map.
- First posted on arXiv 23 Sep 2022.

## Builds on (most cited first, 4 of 4)

- [Structured Attention Networks](https://mlsanity.com/paper/1702.00887/) (2017)
- [Learning to Compose Task-Specific Tree Structures](https://mlsanity.com/paper/1707.02786/) (2017)
- [Learning to Compose Words into Sentences with Reinforcement Learning](https://mlsanity.com/paper/1611.09100/) (2016)
- [Guiding Symbolic Natural Language Grammar Induction via Transformer-Based Sequence Probabilities](https://mlsanity.com/paper/2005.12533/) (2020)

## Built on by (most cited first, 1 of 1)

- [Activity Grammars for Temporal Action Segmentation](https://mlsanity.com/paper/2312.04266/) (2023)

## Abstract (arXiv)

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.