GrammarSHAP: An Efficient Model-Agnostic and Structure-Aware NLP Explainer

Edoardo Mosca, Defne Demirtürk, Luca Mülln, Fabio Raffagnato, Georg Groh

TL;DR: We leverage constituency parsing to propose a model-agnostic hierarchical explainer that extends the SHAP framework.

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.

Track: Archival (will appear in ACL workshop proceedings)