2 papers
cs.CL2020
Gradient-based Analysis of NLP Models is Manipulable
Junlin Wang, Jens Tuyls, Eric Wallace +1
Gradient-based analysis methods, such as saliency map visualizations and adversarial input perturbations, have found widespread use in interpreting neural NLP models due to their s…
cs.CL2019
AllenNLP Interpret: A Framework for Explaining Predictions of NLP Models
Eric Wallace, Jens Tuyls, Junlin Wang +3
Neural NLP models are increasingly accurate but are imperfect and opaque---they break in counterintuitive ways and leave end users puzzled at their behavior. Model interpretation m…