Feature Attribution Methods
Related Papers
Incorporating Priors with Feature Attribution on Text Classification
AbstractFeature attribution methods, proposed recently, help users interpret the predictions of complex models. Our approach integrates feature attributions into the objective function to allow machine learning practitioners to incorporate priors …...
Explainable Event Detection with Event Trigger Identification as Rationale Extraction
AbstractMost event detection methods act at the sentence-level and focus on identifying sentences related to a particular event. However, identifying certain parts of a sentence that act as event triggers …...
Incorporating Attribution Importance for Improving Faithfulness Metrics
AbstractFeature attribution methods (FAs) are popular approaches for providing insights into the model reasoning process of making predictions. The more faithful a FA is, the more accurately it reflects which …...
The Solvability of Interpretability Evaluation Metrics
AbstractFeature attribution methods are popular for explaining neural network predictions, and they are often evaluated on metrics such as comprehensiveness and sufficiency. In this paper, we highlight an intriguing property …...