Learning Hierarchical Multi-Category Text Classification Models

Posted in Science on August 04, 2008


Learning Hierarchical Multi-Category Text Classification Models

Lecture slides:

  • Hierarchical Multilabel Classification:
  • Frequently used learning strategies for hierarchies
  • Max-margin Structured output approach
  • Loss functions for hierarchies
  • Optimization problem
  • Marginalized problem
  • Efficient optimization
  • Conditional Gradient-based training
  • Experiments
  • Microlabel prediction quality: whole tree
  • Levelwise F1
  • Optimization efficiency
  • Conclusions

Author: Juho Rousu, University of Helsinki

Watch Video

Tags: Science, Lectures, Computer Science, VideoLectures.Net, Text Mining