Definition Benchmark for Language Models

This rapository contains the WDLaMPro dataset and the scripts to evaluate BERT, ROBERTA and GPT-2 models on this dataset.

You can download WDLAMPro dataset here.

Citation

If you use WDLaMPro please cite the following paper:

@inproceedings{senel-schutze-2021-wink,
    title = "Does She Wink or Does She Nod? A Challenging Benchmark for Evaluating Word Understanding of Language Models",
    author = {Senel, Lutfi Kerem  and
      Sch{\"u}tze, Hinrich},
    booktitle = "Proceedings of the 16th Conference of the European Chapter of the Association for Computational Linguistics: Main Volume",
    month = apr,
    year = "2021",
    address = "Online",
    publisher = "Association for Computational Linguistics",
    url = "https://aclanthology.org/2021.eacl-main.42",
    pages = "532--538",
}