NAACL 2021: Reproducibility Material for Submission #344
Try our tokenization repair methods in the interactive web demo.
Evaluation web application
Click through our benchmarks and get a visualisation of the results in the evaluation web app.
The data contains our benchmarks described in the paper, as well as trained models and predicted sequences from all our methods (1GB compressed). In addition, you can download our training data (6GB compressed).
The code comes with a Docker setup for easy reproducibility. A readme file in the code directory explains how to setup the Docker container. If you are not familiar with Docker, please visit docker.com.
The Docker container allows you to try our methods interactively, run them on our benchmarks (or on yours!), and run the evaluation. Make targets simplify the program calls and give further explanations. It is really fun and simple, we promise!
The latest version is 1.1.2 (December 2, 2020).