# Learning grammar with a divide-and-concur neural network

arXiv: https://arxiv.org/abs/2201.07341 · HTML: https://mlsanity.com/paper/2201.07341/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 7 of its 24 references that are in the map.
- First posted on arXiv 18 Jan 2022.

## Builds on (most cited first, 7 of 7)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [The Lottery Ticket Hypothesis: Finding Sparse, Trainable Neural Networks](https://mlsanity.com/paper/1803.03635/) (2018)
- [It's Hard for Neural Networks To Learn the Game of Life](https://mlsanity.com/paper/2009.01398/) (2020)
- [Reconstructing cellular automata rules from observations at nonconsecutive times](https://mlsanity.com/paper/2012.02179/) (2020)
- [Learning Without Loss](https://mlsanity.com/paper/1911.00493/) (2019)
- [Avoiding Traps in Nonconvex Problems](https://mlsanity.com/paper/2106.05206/) (2021)

## Abstract (arXiv)

We implement a divide-and-concur iterative projection approach to context-free grammar inference. Unlike most state-of-the-art models of natural language processing, our method requires a relatively small number of discrete parameters, making the inferred grammar directly interpretable -- one can read off from a solution how to construct grammatically valid sentences. Another advantage of our approach is the ability to infer meaningful grammatical rules from just a few sentences, compared to the hundreds of gigabytes of training data many other models employ. We demonstrate several ways of applying our approach: classifying words and inferring a grammar from scratch, taking an existing grammar and refining its categories and rules, and taking an existing grammar and expanding its lexicon as it encounters new words in new data.