Papers by Paul Resnick
Extractive Adversarial Networks: High-Recall Explanations for Identifying Personal Attacks in Social Media Posts (D18-1)
Copied to clipboard
| Challenge: | Existing work on explaining classifier decisions has not addressed local feature redundancy . a common way to explain why a model classified an example is to extract a sparse subset of features that were responsible for the decision . |
| Approach: | They propose an adversarial method for producing high-recall explanations of text classifier decisions . they use a method which scans the residual of attention for remaining predictive signal . |
| Outcome: | The proposed method produces high-recall explanations of text classifier decisions . it uses a set of human-annotated personal attacks to evaluate the impact . |