Optimal and efficient text counterfactuals using Graph Neural Networks

Dimitris Lymperopoulos, Maria Lymperaiou, Giorgos Filandrianos, Giorgos Stamou

Track: Full paper

Keywords: counterfactual/contrastive explanations, transparency, text-to-text generation

TL;DR: A framework for optimal and controllable counterfactual edits on text using graph assignment algorithms and Graph Neural Networks for speedup

Abstract: As NLP models become increasingly integral to decision-making processes, the need for explainability and interpretability has become paramount. In this work, we propose a framework that achieves the aforementioned by generating semantically edited inputs, known as counterfactual interventions, which change the model prediction, thus providing a form of counterfactual explanations for the model. We frame the search for optimal counterfactual interventions as a graph assignment problem and employ a GNN to solve it, thus achieving high efficiency. We test our framework on two NLP tasks - binary sentiment classification and topic classification - and show that the generated edits are contrastive, fluent and minimal, while the whole process remains significantly faster than other state-of-the-art counterfactual editors.

Submission Number: 3