- By:
- Yoon, Hong Jun ; Robinson, Sarah; Christian, James B; Qiu, John X; Tourassi, Georgia
- Page Number:
- 345-348
- Book Title:
- 2018 IEEE EMBS International Conference on Biomedical & Health Informatics (BHI)
- Publication Date:
- April 1, 2024
- Publisher Location:
- IEEE, New Jersey, United States of America
- Conference Name:
- Biomedical and Health Informatics (BHI 2018)
- Conference Location:
- Las Vegas, Nevada, United States of America
- Conference Sponsor:
- IEEE
- View DOI Listing:
- https://doi.org/10.1109/BHI.2018.8333439
Abstract
Convolutional Neural Networks (CNN) have recently demonstrated effective performance in many Natural Language Processing tasks. In this study, we explore a novel approach for pruning a CNN's convolution filters using our new data-driven utility score. We have applied this technique to an information extraction task of classifying a dataset of cancer pathology reports by cancer type, a highly imbalanced dataset. Compared to standard CNN training, our new algorithm resulted in a nearly .07 increase in the micro-averaged F1-score and a strong .22 increase in the macro-averaged F1-score using a model with nearly a third fewer network weights. We show how directly utilizing a network's interpretation of data can result in strong performance gains, particularly with severely imbalanced datasets.
