Explaining Sentiment Classification with Synthetic Exemplars and Counter-Exemplars

You are here

TitleExplaining Sentiment Classification with Synthetic Exemplars and Counter-Exemplars
Publication TypeConference Paper
Year of Publication2020
AuthorsLampridis, O, Guidotti, R, Ruggieri, S
Secondary AuthorsAppice, A, Tsoumakas, G, Manolopoulos, Y, Matwin, S
Conference NameDiscovery Science
Date Published2020//
PublisherSpringer International Publishing
Conference LocationCham
ISBN Number978-3-030-61527-7
AbstractWe 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.
URLhttps://link.springer.com/chapter/10.1007/978-3-030-61527-7_24
DOI10.1007/978-3-030-61527-7_24
Research Project: