TX-Ray: Quantifying and Explaining Model-Knowledge Transfer in (Un-)Supervised NLP

2 code implementations • 2 Dec 2019 • Nils Rethmeier, Vageesh Kumar Saxena, Isabelle Augenstein

While state-of-the-art NLP explainability (XAI) methods focus on explaining per-sample decisions in supervised end or probing tasks, this is insufficient to explain and quantify model knowledge transfer during (un-)supervised training.

Explainable Artificial Intelligence (XAI) Model Compression +1