An application for semantic markup of biodiversity documents

ABSTRACT

We would like to demonstrate a machine-learning based semantic markup system that may be used to reformat free-text biodiversity documents in XML format for digital libraries. We named the system MARTT II. It is built on the MARTT engine described in [1], but with new components for example a parallel markup engine using the unsupervised learning algorithm described in [2]. The double Is in the name stand for Intuitive Interaction, which is our goal to make the system truly easy to use. They also mean the system supports two different automated markup engines, allowing the user to choose either one to use and make comparisons between the two.

REFERENCES

• 1: Hong Cui , P. Bryan Heidorn, The reusability of induced knowledge for the automatic semantic markup of taxonomic descriptions, Journal of the American Society for Information Science and Technology, v.58 n.1, p.133-149, January 2007 [doi>10.1002/asi.v58:1]
• 2: Cui, H. (2008). Unsupervised learning for semantic markup of biodiversity literature. JDCL 2008.

INDEX TERMS

Primary Classification:
  H. Information Systems
  H.3 INFORMATION STORAGE AND RETRIEVAL
      H.3.7 Digital Libraries
          Subjects: Collection

Additional Classification:
  H. Information Systems
  H.3 INFORMATION STORAGE AND RETRIEVAL
      H.3.7 Digital Libraries
          Subjects: Systems issues

General Terms:
Algorithms, Design

Keywords:
XML, biodiversity informatics, morphological description, natural heritage literature, semantic annotation, semantic markup, supervised machine learning, unsupervised machine learning