Material Detail

Expanding a Gazetteer-Based Approach for Geo-Parsing Disease Alerts

Expanding a Gazetteer-Based Approach for Geo-Parsing Disease Alerts

This video was recorded at 25th International Conference on Machine Learning (ICML), Helsinki 2008. Discovering in a text the geographic references it may contain, is a task that human readers perform using both their lexical and contextual knowledge. Using a gazetteer to label such targeted references in a dataset, this paper proposes an approach to learning the context in which they appear and by this means extending the prior knowledge encoded in the gazetteer. The present work was carried in the particular framework of a system for disease outbreak alerts detection and geo-indexing.

Quality

  • User Rating
  • Comments
  • Learning Exercises
  • Bookmark Collections
  • Course ePortfolios
  • Accessibility Info

More about this material

Comments

Log in to participate in the discussions or sign up if you are not already a MERLOT member.