DISK-CSV: Distilling Interpretable Semantic Knowledge with a Class Semantic Vector
Housam Khalifa Bashier, Mi-Young Kim, Randy Goebel
Interpretability and Analysis of Models for NLP Long paper Paper
You can open the pre-recorded video in separate windows.
Abstract:
Neural networks (NN) applied to natural language processing (NLP) are becoming deeper and more complex, making them increasingly difficult to understand and interpret. Even in applications of limited scope on fixed data, the creation of these complex ``black-boxes'' creates substantial challenges for debugging, understanding, and generalization. But rapid development in this field has now lead to building more straightforward and interpretable models. We propose a new technique (DISK-CSV) to distill knowledge concurrently from any neural network architecture for text classification, captured as a lightweight interpretable/explainable classifier. Across multiple datasets, our approach achieves better performance than the target black-box. In addition, our approach provides better explanations than existing techniques.
NOTE: Video may display a random order of authors.
Correct author list is at the top of this page.