References for automated text processing

• Mailing Lists
• Verwaltet von Lothar Lemnitzer's course on Text Technology These slides are useful for the course:
  • Lemnitzer's slides on character encoding
  • Lemnitzer's slides on XML These slides are just generally useful:
  • Lemnitzer's slides on XML DTDs
  • Lemnitzer's slides on XML Schemas
  • Lemnitzer's slides on XPath
  • Lemnitzer's slides on XSL Transformations
  • Lemnitzer's slides on Tokenization
  • Lemnitzer's slides on Sentence Segmentation
  • Lemnitzer's slides on Tag sets
  • Lemnitzer's slides on Rule-based disambiguation
  • Lemnitzer's slides on Lexical Chains

Software

• The Proteus Project (NYU)
• The Penn Treebank Project