DFKI-LT - Learning Explanations From Language Data

David Harbecke, Robert Schwarzenberg, Christoph Alt
Learning Explanations From Language Data
3 EMNLP Workshop on Interpreting and Analysing Neural Networks for NLP (BlackboxNLP), Brussels, Belgium, EMNLP, 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.
 
Files: BibTeX, emnlp-learning-explanations.pdf