Statements (28)
Predicate | Object |
---|---|
gptkbp:instanceOf |
research
|
gptkbp:aimsTo |
enable trust in NLP applications
improve transparency of NLP systems make NLP models more interpretable |
gptkbp:appliesTo |
machine translation
question answering sentiment analysis text classification named entity recognition |
gptkbp:focusesOn |
natural language processing
explainable artificial intelligence |
https://www.w3.org/2000/01/rdf-schema#label |
Explainable AI for NLP
|
gptkbp:importantFor |
gptkb:legislation
user trust debugging NLP models |
gptkbp:includes |
model interpretability
explanation generation feature attribution |
gptkbp:relatedTo |
ethics in AI
accountability in AI fairness in AI |
gptkbp:uses |
gptkb:LIME
gptkb:SHAP counterfactual explanations saliency maps attention visualization |
gptkbp:bfsParent |
gptkb:NAACL_2019
|
gptkbp:bfsLayer |
6
|