Classification responses provided by Multi Layer Perceptrons (MLPs) can be explained by means of propositional rules. So far, many rule extraction techniques have been proposed for shallow MLPs, but not for Convolutional Neural Networks (CNNs). To fill this gap, this work presents a new rule extraction method applied to a typical CNN architecture used in Sentiment Analysis (SA). We focus on the textual data on which the CNN is trained with “tweets” of movie reviews. Its architecture includes an input layer representing words by “word embeddings”, a convolutional layer, a max-pooling layer, followed by a fully connected layer. Rule extraction is performed on the fully connected layer, with the help of the Discretized Interpretable Multi Layer Perceptron (DIMLP). This transparent MLP architecture allows us to generate symbolic rules, by precisely locating axis-parallel hyperplanes. Experiments based on cross-validation emphasize that our approach is more accurate than that based on SVMs and decision trees that substitute DIMLPs. Overall, rules reach high fidelity and the discriminative n-grams represented in the antecedents explain the classifications adequately. With several test examples we illustrate the n-grams represented in the activated rules. They present the particularity to contribute to the final classification with a certain intensity.
Transformer failure diagnosis by different rule extraction method: a review
