3 papers
cs.LG2024
Rethinking Distance Metrics for Counterfactual Explainability
Joshua Nathaniel Williams, Anurag Katakkar, Hoda Heidari +1
Counterfactual explanations have been a popular method of post-hoc explainability for a variety of settings in Machine Learning. Such methods focus on explaining classifiers by gen…
cs.CL2021
Towards Language Modelling in the Speech Domain Using Sub-word Linguistic Units
Anurag Katakkar, Alan W Black
Language models (LMs) for text data have been studied extensively for their usefulness in language generation and other downstream tasks. However, language modelling purely in the…
cs.CL2021
Practical Benefits of Feature Feedback Under Distribution Shift
Anurag Katakkar, Clay H. Yoo, Weiqin Wang +2
In attempts to develop sample-efficient and interpretable algorithms, researcher have explored myriad mechanisms for collecting and exploiting feature feedback (or rationales) auxi…