@inproceedings{494382eb88204c02bccd993e4eccf03c,
title = "GrammarSHAP: An Efficient Model-Agnostic and Structure-Aware NLP Explainer",
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{\textquoteright}s constituency parsing to generate hierarchical importance scores.",
author = "Edoardo Mosca and Defne Demit{\"u}rk and Luca M{\"u}lln and Fabio Raffagnato and Georg Groh",
note = "Publisher Copyright: {\textcopyright} 2022 Association for Computational Linguistics.; 1st Workshop on Learning with Natural Language Supervision, LNLS 2022 ; Conference date: 26-05-2022",
year = "2022",
language = "English",
series = "LNLS 2022 - 1st Workshop on Learning with Natural Language Supervision, Proceedings of the Workshop",
publisher = "Association for Computational Linguistics (ACL)",
pages = "10--16",
editor = "Jacob Andreas and Karthik Narasimhan and Aida Nematzadeh",
booktitle = "LNLS 2022 - 1st Workshop on Learning with Natural Language Supervision, Proceedings of the Workshop",
}