Explaining Sentiment Classification with Synthetic Exemplars and Counter-Exemplars
| Title | Explaining Sentiment Classification with Synthetic Exemplars and Counter-Exemplars |
| Publication Type | Conference Paper |
| Year of Publication | 2020 |
| Authors | Lampridis, O, Guidotti, R, Ruggieri, S |
| Secondary Authors | Appice, A, Tsoumakas, G, Manolopoulos, Y, Matwin, S |
| Conference Name | Discovery Science |
| Date Published | 2020// |
| Publisher | Springer International Publishing |
| Conference Location | Cham |
| ISBN Number | 978-3-030-61527-7 |
| Abstract | 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. |
| URL | https://link.springer.com/chapter/10.1007/978-3-030-61527-7_24 |
| DOI | 10.1007/978-3-030-61527-7_24 |
Research Line: