@inproceedings{mosca-etal-2022-grammarshap,
    title = "{G}rammar{SHAP}: An Efficient Model-Agnostic and Structure-Aware {NLP} Explainer",
    author = {Mosca, Edoardo  and
      Demirt{\"u}rk, Defne  and
      M{\"u}lln, Luca  and
      Raffagnato, Fabio  and
      Groh, Georg},
    editor = "Andreas, Jacob  and
      Narasimhan, Karthik  and
      Nematzadeh, Aida",
    booktitle = "Proceedings of the First Workshop on Learning with Natural Language Supervision",
    month = may,
    year = "2022",
    address = "Dublin, Ireland",
    publisher = "Association for Computational Linguistics",
    url = "https://aclanthology.org/2022.lnls-1.2",
    doi = "10.18653/v1/2022.lnls-1.2",
    pages = "10--16",
    abstract = "Interpreting NLP models is fundamental for their development as it can shed light on hidden properties and unexpected behaviors. However, while transformer architectures exploit contextual information to enhance their predictive capabilities, most of the available methods to explain such predictions only provide importance scores at the word level. This work addresses the lack of feature attribution approaches that also take into account the sentence structure. We extend the SHAP framework by proposing GrammarSHAP{---}a model-agnostic explainer leveraging the sentence{'}s constituency parsing to generate hierarchical importance scores.",
}