Intrinsically Interpretable Document Classification via Concept Lattices

Ch. 2. P. 9–22.

Parakal E. G., Kuznetsov S.

Editor of translation: Kuznetsov S., Napoli A., Rudolph S.

Explanations for the predictions made by Machine Learning (ML) models are best framed in terms of
abstract, high-level concepts that are easily comprehensible to human beings. The use of such concepts
constitutes a subfield of interpretability methods known as concept-based explanations. This work uses
concept-based explanations to build an intrinsically interpretable document classifier using a combination
of Formal Concept Analysis (FCA) and approaches from applied graph theory. FCA is used to formalize
the vague notion of concepts in terms of the formal concepts found in the concept lattices of various
document classes. The graph of the lattice covering relation helps to utilize the topological information
present in the document-class concept lattices for classifying documents. Finally, the formal concepts
that made the strongest contributions to the predictions of the document classifier are revealed, along
with their intents; thereby making their contribution more comprehensible to human beings.

Keywords: natural language processing, Formal Concept Analysis, explainable artificial intelligence

In book

Proceedings of the 10th International Workshop "What can FCA do for Artificial Intelligence?"

Vol. 3233. , CEUR Workshop Proceedings, 2022.