Explainable Authorship Identification in Cultural Heritage Applications: Analysis of a New Perspective
This addresses the problem of interpretability for scholars in cultural heritage, but it is incremental as it applies existing methods to a new domain.
The paper tackled the lack of explainability in Authorship Identification (AId) systems, which hinders their practical use, by applying existing XAI techniques to AId tasks and found that while they offer initial progress, more work is needed for effective integration into scholars' workflows.
While a substantial amount of work has recently been devoted to enhance the performance of computational Authorship Identification (AId) systems, little to no attention has been paid to endowing AId systems with the ability to explain the reasons behind their predictions. This lacking substantially hinders the practical employment of AId methodologies, since the predictions returned by such systems are hardly useful unless they are supported with suitable explanations. In this paper, we explore the applicability of existing general-purpose eXplainable Artificial Intelligence (XAI) techniques to AId, with a special focus on explanations addressed to scholars working in cultural heritage. In particular, we assess the relative merits of three different types of XAI techniques (feature ranking, probing, factuals and counterfactual selection) on three different AId tasks (authorship attribution, authorship verification, same-authorship verification) by running experiments on real AId data. Our analysis shows that, while these techniques make important first steps towards explainable Authorship Identification, more work remains to be done in order to provide tools that can be profitably integrated in the workflows of scholars.