Explaining sentiment classification with synthetic exemplars and counter-exemplars

Lampridis O., Guidotti R., Ruggieri S.

Fidelity  Encoding (memory)  Stability (learning theory)  Article  Visual Explanations  Selection (genetic algorithm)  Deep Learning Applications in Healthcare  Set (abstract data type)  Interpretable Models  Black Box Models  Computer Science  Natural language processing  Explainable sentiment classification  Word Representation  Explainable Artificial Intelligence  Artificial Intelligence  Natural Language Processing  Telecommunications  Topic Modeling  Computer science  Physical Sciences  Programming language  Synthetic exemplars  Machine learning  Artificial intelligence 

We present xspells, a model-agnostic local approach for explaining the decisions of a black box model for sentiment classification of short texts. The explanations provided consist of a set of exemplar sentences and a set of counter-exemplar sentences. The former are examples classified by the black box with the same label as the text to explain. The latter are examples classified with a different label (a form of counter-factuals). Both are close in meaning to the text to explain, and both are meaningful sentences - albeit they are synthetically generated. xspells generates neighbors of the text to explain in a latent space using Variational Autoencoders for encoding text and decoding latent instances. A decision tree is learned from randomly generated neighbors, and used to drive the selection of the exemplars and counter-exemplars. We report experiments on two datasets showing that xspells outperforms the well-known lime method in terms of quality of explanations, fidelity, and usefulness, and that is comparable to it in terms of stability.

Source: LECTURE NOTES IN COMPUTER SCIENCE, vol. 12323, pp. 357-373. Thessaloniki, Greece, 19-21/10/2020

Metrics