[ Skip to the content ]

Institute of Formal and Applied Linguistics Wiki

[ Back to the navigation ]

You are here: start » padt

Differences

This shows you the differences between two versions of the page.

Link to this comparison view

Both sides previous revision Previous revision
Next revision 		Previous revision
Next revision Both sides next revision
padt:start [2011/05/31 13:29]
smrz 		padt:start [2013/05/27 17:35]
zeman TODO: Treex reader.
Line 2: Line 2:
  
 http://ufal.mff.cuni.cz/padt/online/ http://ufal.mff.cuni.cz/padt/online/
- 
-===== Overview ===== 
  
 ===== Setup ===== ===== Setup =====
Line 9: Line 7:
 Install [[http://ufal.mff.cuni.cz/~pajas/tred/|TrEd]] including the [[http://ufal.mff.cuni.cz/~pajas/tred/extensions/padt/documentation/|padt]] and [[http://ufal.mff.cuni.cz/~pajas/tred/extensions/elixir/documentation/|elixir]] extensions from the default TrEd repository http://ufal.mff.cuni.cz/~pajas/tred/extensions/. Install [[http://ufal.mff.cuni.cz/~pajas/tred/|TrEd]] including the [[http://ufal.mff.cuni.cz/~pajas/tred/extensions/padt/documentation/|padt]] and [[http://ufal.mff.cuni.cz/~pajas/tred/extensions/elixir/documentation/|elixir]] extensions from the default TrEd repository http://ufal.mff.cuni.cz/~pajas/tred/extensions/.
  
-The SVN repository of the PADT project is https://svn.ms.mff.cuni.cz/svn/padt/. A working copy is accessible at /net/projects/ace/data/arabic/PADT/ on the UFAL network.+The SVN repository of the PADT project is https://svn.ms.mff.cuni.cz/svn/padt/. A working copy is accessible at ''/net/projects/padt'' on the ÚFAL network.
  
 The project's data are stored in the main subdirectory ''data'', which is split further into ''Prague'', ''Penn'', and ''ElixirFM'', explained below. The project's data are stored in the main subdirectory ''data'', which is split further into ''Prague'', ''Penn'', and ''ElixirFM'', explained below.
Line 18: Line 16:
 tred /net/projects/ace/data/arabic/PADT/data/Prague/AEP/UMH_ARB_20040407.0001.{morpho,syntax}.pml tred /net/projects/ace/data/arabic/PADT/data/Prague/AEP/UMH_ARB_20040407.0001.{morpho,syntax}.pml
 </code> </code>
 +
 +For improved quality of display of the various scripts and trees types, you can use the following setup in TrEd's config file, or similar:
 +
 +<file>
 +Font = "family:DejaVu Sans Condensed, size:14, weight:normal"
 +
 +NodeXSkip = 30;
 +NodeYSkip = 10;
 +</file>
  
 ===== Locations ===== ===== Locations =====
Line 42: Line 49:
  
 The code base for the PADT project, i.e. for annotation, display, and processing of the data, is the TrEd's ''padt'' extension, and its ''elixir'' extension that is a dependency for ''padt''. The code base for the PADT project, i.e. for annotation, display, and processing of the data, is the TrEd's ''padt'' extension, and its ''elixir'' extension that is a dependency for ''padt''.
- 
 ===== Agenda ===== ===== Agenda =====
 +
 +  * Write a block to read the PADT 2.0 data in Treex. An XML schema is needed.
  
 Focus on paragraphs/sentences that miss PADT-Morpho annotation, esp. non-annotated headlines: Focus on paragraphs/sentences that miss PADT-Morpho annotation, esp. non-annotated headlines:
Line 58: Line 66:
 </code> </code>
  
-===== References ===== 
  
 +There are some other tasks that have been partially solved in PADT, but need to be refreshed and completed:
 +
 +  * Retrain the CRF++ model for tagging selected morphological categories and apply it to prune remaining morphological ambiguities.
 +  * Refresh and improve the code and rules for converting PATB phrase syntax trees into dependency trees a la PADT.
 +  * Update PADT::Syntax annotation context (level synchronization, non-conflicting bindings). 
 +  * Update PADT::Deeper annotation context (level synchronization, working schemas, modern stylesheets, non-conflicting bindings).
 +  * Improve documentation.
 +
 +===== References =====

[ Back to the navigation ] [ Back to the content ]