首页    期刊浏览 2024年11月27日 星期三
登录注册

文章基本信息

  • 标题:DISK-CSV: Distilling Interpretable Semantic Knowledge with a Class Semantic Vector
  • 本地全文:下载
  • 作者:Housam Khalifa Bashier ; Mi-Young Kim ; Randy Goebel
  • 期刊名称:Conference on European Chapter of the Association for Computational Linguistics (EACL)
  • 出版年度:2021
  • 卷号:2021
  • 页码:3021-3030
  • DOI:10.18653/v1/2021.eacl-main.263
  • 语种:English
  • 出版社:ACL Anthology
  • 摘要: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.
国家哲学社会科学文献中心版权所有