# Integrating Regular Expressions with Neural Networks via DFA

arXiv: https://arxiv.org/abs/2109.02882 · HTML: https://mlsanity.com/paper/2109.02882/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 9 of its 15 references that are in the map.
- First posted on arXiv 7 Sep 2021.

## Builds on (most cited first, 9 of 9)

- [Distributed Representations of Words and Phrases and their Compositionality](https://mlsanity.com/paper/1310.4546/) (2013)
- [Recent Trends in Deep Learning Based Natural Language Processing](https://mlsanity.com/paper/1708.02709/) (2017)
- [Neural-Symbolic Computing: An Effective Methodology for Principled Integration of Machine Learning and Reasoning](https://mlsanity.com/paper/1905.06088/) (2019)
- [Harnessing Deep Neural Networks with Logic Rules](https://mlsanity.com/paper/1603.06318/) (2016)
- [Neural Symbolic Machines: Learning Semantic Parsers on Freebase with Weak Supervision](https://mlsanity.com/paper/1611.00020/) (2016)
- [Embedding Symbolic Knowledge into Deep Networks](https://mlsanity.com/paper/1909.01161/) (2019)
- [Representing Formal Languages: A Comparison Between Finite Automata and Recurrent Neural Networks](https://mlsanity.com/paper/1902.10297/) (2019)
- [Marrying up Regular Expressions with Neural Networks: A Case Study for Spoken Language Understanding](https://mlsanity.com/paper/1805.05588/) (2018)
- [IterefinE: Iterative KG Refinement Embeddings using Symbolic Knowledge](https://mlsanity.com/paper/2006.04509/) (2020)

## Abstract (arXiv)

Human-designed rules are widely used to build industry applications. However, it is infeasible to maintain thousands of such hand-crafted rules. So it is very important to integrate the rule knowledge into neural networks to build a hybrid model that achieves better performance. Specifically, the human-designed rules are formulated as Regular Expressions (REs), from which the equivalent Minimal Deterministic Finite Automatons (MDFAs) are constructed. We propose to use the MDFA as an intermediate model to capture the matched RE patterns as rule-based features for each input sentence and introduce these additional features into neural networks. We evaluate the proposed method on the ATIS intent classification task. The experiment results show that the proposed method achieves the best performance compared to neural networks and four other methods that combine REs and neural networks when the training dataset is relatively small.