Email Contact: bioie@ldc.upenn.edu
This material is based upon work supported by the National Science Foundation under Grant No.: EIA-0205448
Home
      -Overview
      -About Us/Credits
Resources
      -Data
      -Publications
      -Works of Interest
Documentation
      -User Guide
      -Guided Tour
      -Description of Data
      -Software/Tools
      -Docs for Annotators
Software/Tools
      -WordFreak
      -LAW Workflow System
      -Annotation Database
      -Auto Text Processing
      -TreeEditor
      -Taggers
Archive Releases
 
Printer Friendly Version
 
Mining the Bibliome
Mining the Bibliome
Taggers
 
A summary description of each of the taggers and parsers is provided with these links, along with guidelines for manual annotation.


Contents

  1. Paragraph Taggers:
    Briefly describes how the tagger is used to automatically tag paragraphs using WordFreak.

  2. Sentence Taggers:
    Briefly describes how the tagger is used to automatically tag sentences using WordFreak.

  3. Tokenizer Tagging:
    Briefly describes how the tagger is used to automatically tag tokens using WordFreak.

  4. POS Taggers:
    Briefly describes how annotators and trained POS files use the POS taggers to tag different parts of speech.

  5. Entity Tagging

    • Oncology Entity Tagging:
      Briefly describes how annotators use the oncology entity taggers to tag different oncology related entities using WordFreak.

      • BioTagger Models:
        The BioTagger Models section includes links to the documentation, trained gene modeling data for each respective model, with links to download each tagger.

        • Gene Tagging Models (trained on Biocreative data, Angiogenesis data, Neuroblastoma data, Sanger data, and Sanger + Angiogenesis + Neuroblastoma data)

        • Genomic Variation Models
          • Variation Taggers:
            summary description of the variation tagger which is being developed in the oncology domain. (Jan. '04, HTML, ~2pp.) These advances in technology will be of great value for the entire information extraction field.

        • Malignancy Type Models

    • CYP450 Entity Tagging:
      Briefly describes how annotators use the CYP450 entity taggers to tag different CYP450 related entities using WordFreak.

  6. Relation Taggers

  7. Tree Banking Parser : TBA