Incorporating Priors with Feature Attribution on Text Classification
This work addresses the need for interpretable and fair text classifiers, particularly for mitigating biases and handling limited data, but it is incremental as it builds on existing feature attribution methods.
The paper tackles the problem of incorporating priors into text classification models by integrating feature attributions into the objective function, resulting in reduced unintended biases without performance trade-offs and improved performance in scarce data settings.
Feature 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 in model building. To demonstrate the effectiveness our technique, we apply it to two tasks: (1) mitigating unintended bias in text classifiers by neutralizing identity terms; (2) improving classifier performance in a scarce data setting by forcing the model to focus on toxic terms. Our approach adds an L2 distance loss between feature attributions and task-specific prior values to the objective. Our experiments show that i) a classifier trained with our technique reduces undesired model biases without a trade off on the original task; ii) incorporating priors helps model performance in scarce data settings.