Learning Explanations From Language Data

David Harbecke, Robert Schwarzenberg, Christoph Alt

In: The 2018 EMNLP Workshop BlackboxNLP: Analyzing and Interpreting Neural Networks for NLP - Proceedings of the First Workshop. Analyzing and Interpreting Neural Networks for NLP (BlackboxNLP) located at EMNLP 2018 November 1-1 Brussels Belgium ISBN 978-1-948087-71-1 The Association for Computational Linguistics 2018.


PatternAttribution is a recent method, introduced in the vision domain, that explains classifications of deep neural networks. We demonstrate that it also generates meaningful interpretations in the language domain.


emnlp-learning-explanations.pdf (pdf, 162 KB )

German Research Center for Artificial Intelligence
Deutsches Forschungszentrum für Künstliche Intelligenz