[ NLP root ] 

NLP Software Documentation Index

• Technical support (setting up accounts etc.)
• Directory structure and data description
• How to display and input Czech characters
• Czech alphabet, code page, sorting order, approximate pronunciation, and keyboard layout
• Data description. The main corpus is the current version of the Prague Dependency Treebank (PDT). There are additional data such as the bilingual Czech-English corpus.
• PDT description, division, and placement
• PDT format description (DTD)
• Bilingual corpus description
• Jan Hajic, Barbora Hladká: Tagging Inflective Languages: Prediction of Morphological Categories for a Rich, Structured Tagset (paper for COLING/ACL 98, Montréal) - this paper contains a description of the internal structure of the morphological tags.
• 9800: Data preparation tools
• PDT preparation, checking, and segmentation into training/test data
• 9801: Mike's Parser (probabilistic CFG)
• Collins parser effort: index, pointers, and how-to
• Background about parsing lexicalized grammars (talk given 29th July 1998)
• Tutorial about probabilistic parsing (given in pre-workshop week)
• 9802: Dan's Parser (probabilistic distribution of dependencies)
• Initial description
• Initial result overview
• User's manual
• Results with different sources of morphology
• 9803: Parsing Resources from Bilingual Corpora
• 9804: Eric's Parser (transformation based)
• 9805: The Superparser
• 9806: Evaluation tools
• 9807: Tree viewing tools
• How to run the preliminary version
• 9808: Evaluation run
• 9809: Structured language model adapatation for Czech
• Other papers, talks, etc.
• WS98 NLP project description (Jan's presentation on the opening day): in Microsoft PowerPoint format or in postscript
• Morphology of inflectional languages (Jan's talk in the 2nd pre-workshop week): in Microsoft PowerPoint format or in postscript (part 1, 2, 3)
• Using exponential models for tagging Czech ( postscript )
• Survey of Theoretical and Computational Linguistics (Jones)