Grex is a tool for automatic grammar rule extraction from treebanks created by Santiago Herrera, Caio Corro and Sylvain Kahane. A full description of the method can be found in in the paper. This webpage displays raw results for agreement and word order. A detailed analysis of these results can be found in Section 5 of the paper. You can also download here the raw data in json format and use any tool you want to explore results.

The code is freely available on github. This work was done as part of the Autogramm project.

To cite this work, please use the following reference:

@inproceedings{herrera2024grex,
    title = "Sparse Logistic Regression with High-order Features for Automatic Grammar Rule Extraction from Treebanks",
    author = "Herrera, Santiago and Corro, Caio and Kahane, Sylvain",
    booktitle = "Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation",
    month = may,
    year = "2024",
    address = "Torino, Italia",
    url = "https://arxiv.org/abs/2403.17534",
}

TODO TODO