On Efficiently Representing Regular Languages as RNNs

Code accompanying the ACL 2024 publication "On Efficiently Representing Regular Languages as RNNs".

Getting started with the code

Clone the repository:

$ git clone [email protected]:rycolab/bpdas.git
$ cd bpdas

It may be beneficial to create a new Python virtual environment (e.g., using conda). We aim at Python 3.10 version and above.

You can then install the package in editable mode:

$ pip install -e .

We use pytest to unit test the code. You can run the tests with:

$ pytest tests/