[ Skip to the content ]

Institute of Formal and Applied Linguistics Wiki


[ Back to the navigation ]

Differences

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

Link to this comparison view

Next revision
Previous revision
Next revision Both sides next revision
courses:rg:2011-report-parser [2012/09/26 13:46]
ufal vytvořeno
courses:rg:2011-report-parser [2012/09/27 09:41]
ufal
Line 3: Line 3:
 written by Stephen Tratz and Eduard Hovy (Information Sciences Institute, University of Southern Carolina) written by Stephen Tratz and Eduard Hovy (Information Sciences Institute, University of Southern Carolina)
  
-spoken by Martin Popel+presented by Martin Popel
  
 reported by Michal Novák reported by Michal Novák
  
 ===== Introduction ===== ===== Introduction =====
 +
 +The paper describes a high-quality conversion of Penn Treebank to dependency trees. The authors introduce an improved labeled dependency scheme based on the Stanford's one. In addition, they extend the non-directional easy-first first algorithm of Goldberg and Elhadad to support non-projective trees by adding "move" actions inspired by Nivre's swap-based reordering for shift-reduce parsing. Their parser is capable of producing shallow semantic annotations for prepositions, possesives and noun compounds.
  
  
 ===== Notes ===== ===== Notes =====
 +
 +==== Dependency conversion structure ====
 +
 +  * in general, there are (at least) 3 possible types of dependency labels:
 +    * unlabeled - is it really a set of labels?
 +    * coarse labels of the CoNLL tasks
 +        * 10-20 labels
 +        * for example NMOD is always under a noun - it's an easy task and the result is not quite useful
 +    * their scheme is based on the Stanford's dependency labels
 +
  

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