Year: 2018
Type: conference-paper
Abstract: Local model interpretation methods explain individual predictions by assigning an importance value to each input feature.This value is often determined by measuring the change in confidence when a feature is removed.However, the confidence of neural networks is not a robust measure of model uncertainty.This issue makes reliably judging the importance of the input features difficult.We address this by changing the test-time behavior of neural networks using Deep k-Nearest Neighbors.Without harming text classification accuracy, this algorithm provides a more robust uncertainty metric which we use to generate feature importance values.The resulting interpretations better align with human perception than baseline methods.Finally, we use our interpretation method to analyze model predictions on dataset annotation artifacts.
DOI: 10.18653/v1/w18-5416
Authors: Eric Wallace, Shi Feng, Jordan Boyd-Graber
Institution: University of Maryland, College Park
Language: English
Subfield: Artificial Intelligence
Field: Computer Science
Domain: Physical Sciences
Open Access status: hybrid
OpenAlex ID: W2891020797
