skip to main content
OSTI.GOV title logo U.S. Department of Energy
Office of Scientific and Technical Information

Title: Filter pruning of Convolutional Neural Networks for text classification: A case study of cancer pathology report comprehension

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.

Authors:
ORCiD logo [1];  [2]; ORCiD logo [1];  [1]; ORCiD logo [1]
  1. ORNL
  2. Rice University
Publication Date:
Research Org.:
Oak Ridge National Lab. (ORNL), Oak Ridge, TN (United States)
Sponsoring Org.:
USDOE
OSTI Identifier:
1468241
DOE Contract Number:  
AC05-00OR22725
Resource Type:
Conference
Resource Relation:
Conference: Biomedical and Health Informatics (BHI 2018) - Las Vegas, Nevada, United States of America - 3/4/2018 10:00:00 AM-3/7/2018 10:00:00 AM
Country of Publication:
United States
Language:
English

Citation Formats

Yoon, Hong-Jun, Robinson, Sarah, Christian, Blair, Qiu, John X., and Tourassi, Georgia. Filter pruning of Convolutional Neural Networks for text classification: A case study of cancer pathology report comprehension. United States: N. p., 2018. Web. doi:10.1109/BHI.2018.8333439.
Yoon, Hong-Jun, Robinson, Sarah, Christian, Blair, Qiu, John X., & Tourassi, Georgia. Filter pruning of Convolutional Neural Networks for text classification: A case study of cancer pathology report comprehension. United States. doi:10.1109/BHI.2018.8333439.
Yoon, Hong-Jun, Robinson, Sarah, Christian, Blair, Qiu, John X., and Tourassi, Georgia. Thu . "Filter pruning of Convolutional Neural Networks for text classification: A case study of cancer pathology report comprehension". United States. doi:10.1109/BHI.2018.8333439. https://www.osti.gov/servlets/purl/1468241.
@article{osti_1468241,
title = {Filter pruning of Convolutional Neural Networks for text classification: A case study of cancer pathology report comprehension},
author = {Yoon, Hong-Jun and Robinson, Sarah and Christian, Blair and Qiu, John X. and Tourassi, Georgia},
abstractNote = {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.},
doi = {10.1109/BHI.2018.8333439},
journal = {},
number = ,
volume = ,
place = {United States},
year = {2018},
month = {3}
}

Conference:
Other availability
Please see Document Availability for additional information on obtaining the full-text document. Library patrons may search WorldCat to identify libraries that hold this conference proceeding.

Save / Share: