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
data:start [2007/11/16 15:46]
alexlenci 		data:start [2010/11/01 14:07] (current)
Line 1: Line 1:
-====== Data sets for the evaluation of word space models ======+====== Resources for the evaluation of word space models ======
  
-This page contains a developing list of tasks, sub-tasks and corresponding (sub-)data-sets. 
  
 +===== Ordered by events =====
  
-===== Ordered by task categories ===== +  * [[:data:esslli2008:start|ESSLLI 2008 Shared Tasks]] (for the [[:workshop:esslli:start|Workshop on Distributional Lexical Semantics]]) 
  
  
 +===== Ordered by task categories =====
  
  
 +==== Semantic classification ====
  
 +  * Noun & verb categorization (ESSLLI 2008)
 +    * [[:data:esslli2008:Concrete Noun Categorization|semantic categories of concrete nouns]]
 +    * [[:data:esslli2008:Abstract/Concrete Nouns Discrimination|abstract vs. concrete nouns]]
 +    * [[:data:esslli2008:Verb Categorization|Levin-style verb classes]]
  
-==== Task 1: Categorization ====+==== Free association ====
  
-Categorization tasks play a prominent role in cognitive research on concepts. In this type of tasks, subjects +  * [[:data:esslli2008:Correlation with Free Association Norms|Correlation with free association norms]] (ESSLLI 2008) 
-are typically asked to assign experimental items - objects, images, words - +    * discrimination: strong association vs. non-associated 
-to a given category or to group together items belonging to the same category. +    * correlation: regression modelling of association strength 
-Since categorization presupposes an understanding of the relationship between the items in a category, it is regarded as a key source of evidence on the organization and structure of the human conceptual system.+    * prediction of most common responses (strongest associations)
  
-In the present task, computational models will be tested on their ability to properly group 
-words into semantic categories. The task is organized into three sub-tasks, focussing on different areas 
-of the lexicon and/or semantic dimensions: 
  
-  * [[Concrete Nouns Categorization]] +==== Property generation ====
-  * [[Verb Categorization]] +
-  * [[Abstract/Concrete Nouns Discrimination]]+
  
-==== Task 2 ====+  * [[:data:esslli2008:Comparison with Speaker-Generated Features|Prediction of speaker-generated semantic features]]
  
-  * link to data set 
-  * link to data set 
  
-==== Task 3: Property Generation ==== 
  
-  * [[Comparison with Speaker-Generated Features]] 

You are here: start » data