"Honey, Tell Me What's Wrong", Global Explanation of Textual Discriminative Models through Cooperative Generation
This addresses the need for model explanations in scenarios where data is unavailable, such as for confidentiality, offering a global overview of model behavior.
The paper tackles the problem of explaining complex machine learning models without needing initial data, proposing Therapy, a global and model-agnostic explanation method for text that generates explanations through cooperative generation, and it shows competitive performance with methods that rely on input samples, outperforming them when samples are not specific to the model.
The ubiquity of complex machine learning has raised the importance of model-agnostic explanation algorithms. These methods create artificial instances by slightly perturbing real instances, capturing shifts in model decisions. However, such methods rely on initial data and only provide explanations of the decision for these. To tackle these problems, we propose Therapy, the first global and model-agnostic explanation method adapted to text which requires no input dataset. Therapy generates texts following the distribution learned by a classifier through cooperative generation. Because it does not rely on initial samples, it allows to generate explanations even when data is absent (e.g., for confidentiality reasons). Moreover, conversely to existing methods that combine multiple local explanations into a global one, Therapy offers a global overview of the model behavior on the input space. Our experiments show that although using no input data to generate samples, Therapy provides insightful information about features used by the classifier that is competitive with the ones from methods relying on input samples and outperforms them when input samples are not specific to the studied model.