activity
20182021
most citedExplaining Natural Language Processing Classifiers with Occlusion and Language Modeling

3 citations · 4 across the 3 of their papers we have counts for

collaborators

6 papers

cs.CL20213 cited

Explaining Natural Language Processing Classifiers with Occlusion and Language Modeling

David Harbecke

Deep neural networks are powerful statistical learners. However, their predictions do not come with an explanation of their process. To analyze these models, explanation methods ar…

cs.CL2020

Considering Likelihood in NLP Classification Explanations with Occlusion and Language Modeling

David Harbecke, Christoph Alt

Recently, state-of-the-art NLP models gained an increasing syntactic and semantic understanding of language, and explanation methods are crucial to understand their decisions. Occl…

cs.CL20191 cited

Layerwise Relevance Visualization in Convolutional Text Graph Classifiers

Robert Schwarzenberg, Marc Hübner, David Harbecke +2

Representations in the hidden layers of Deep Neural Networks (DNN) are often hard to interpret since it is difficult to project them into an interpretable domain. Graph Convolution…

cs.CL2019

Neural Vector Conceptualization for Word Vector Space Interpretation

Robert Schwarzenberg, Lisa Raithel, David Harbecke

Distributed word vector spaces are considered hard to interpret which hinders the understanding of natural language processing (NLP) models. In this work, we introduce a new method…

cs.CL2019

Train, Sort, Explain: Learning to Diagnose Translation Models

Robert Schwarzenberg, David Harbecke, Vivien Macketanz +2

Evaluating translation models is a trade-off between effort and detail. On the one end of the spectrum there are automatic count-based methods such as BLEU, on the other end lingui…

cs.CL2018

Learning Explanations from Language Data

David Harbecke, Robert Schwarzenberg, Christoph Alt

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