DFKI-NLP
DFKI-NLP
Home
News
People
Publications
Projects
Datasets
Contact
Light
Dark
Automatic
Explainability
Considering Likelihood in NLP Classification Explanations with Occlusion and Language Modeling
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. Occlusion is a well established method that provides explanations on …
Cite
×