[ 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

Both sides previous revision Previous revision
Next revision Both sides next revision
courses:rg:reranking-by-multitask-learning [2010/10/18 17:39]
popel
courses:rg:reranking-by-multitask-learning [2010/10/22 13:56]
vandas Basics of commentars and discussion after the reading
Line 14: Line 14:
  
 ===== Opinions on the paper ===== ===== Opinions on the paper =====
 +
 +TODO: suggestions to solve/comment
 +
 +Research group suggested that they extract only those features that has a nonzero weight in any of W.
 +
 +Comments by M. Popel:
 +Feature pruning using a treshold: When you have limited data, according to this work it worth to try a good feature than to set a treshold.
 +
 +We were arguing about the number of features used in sets. It is unlikely that they could somehow get the fixed number of features.
 +(I suppose that it is just number of input features, if they were really used is not clear.)
 +
 +Every feature is only fired at the sentence where the conditions are met.
 +Example: 500 sentences, every sentence has just one N-best list. That means 500 weight vectors
 +
 +We argued about hashing the features together - in what way are they hashed?
  
  

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