The FCG PropBank system facilitates the learning of large-scale broad-coverage computational construction grammars from PropBank-annotated corpora.

Getting Started

• For most users, the easiest way to interact with the FCG PropBank system is through its Python API. A tutorial is available here. There is no need to clone the entire repository. The tutorial should run perfectly fine with the pyfcg library installed via pip.
• Source code of the grammar learning method as part of the Babel framework: Repository link.

How to cite?

Van Eecke, P., & Beuls, K. (2026). A Method for Learning Large-Scale Computational Construction Grammars from Semantically Annotated Corpora. In: Proceedings of the 30th Conference on Computational Natural Language Learning (pp. 213-226).