Differences

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

Link to this comparison view

Next revision
Previous revision
data:esslli2008:concrete_noun_categorization [2008/03/28 00:00]
127.0.0.1 external edit
data:esslli2008:concrete_noun_categorization [2010/11/01 14:07] (current)
Line 1: Line 1:
-====== Task 1.a - Concrete Noun Categorization ======+====== Task 2a - Concrete Noun Categorization ======
  
  
Line 7: Line 7:
 The goal of the sub-task is to group concrete nouns into semantic categories. The goal of the sub-task is to group concrete nouns into semantic categories.
  
-The {{concnouns.categorization.dataset.txt.gz |data set}} consists of 44 concrete nouns, belonging to 6 semantic categories (four natural and two man-made). The nouns are included in the feature norms described in McRae et al. (2005) (cf. [[comparison_with_speaker-generated_features|Task3]]).+The {{concnouns.categorization.dataset.txt.gz |data set}} consists of 44 concrete nouns, belonging to 6 semantic categories (four natural and two man-made). The nouns are included in the feature norms described in McRae et al. (2005) (cf. [[comparison_with_speaker-generated_features|Task 3]]).
  
  
Line 43: Line 43:
 1. **quantitative evaluation** - results will be evaluated with respect to the two measures for cluster quality available in CLUTO: //purity// and //entropy// (cf. Zhao, Y. and G. Karypis (2002), "Evaluation of Hierarchical Clustering Algorithms for Document Datasets", in //CIKM 2002//).  1. **quantitative evaluation** - results will be evaluated with respect to the two measures for cluster quality available in CLUTO: //purity// and //entropy// (cf. Zhao, Y. and G. Karypis (2002), "Evaluation of Hierarchical Clustering Algorithms for Document Datasets", in //CIKM 2002//). 
  
-2. **qualitative evaluation** - participants will be asked to perform a fine-grained error analysis, focussing on critical nouns, hard classes, etc. ({{data:qualitativeanalysis.nouncat.zip| recommended qualitative evaluation criteria}})+2. **qualitative evaluation** - participants will be asked to perform a fine-grained error analysis, focussing on critical nouns, hard classes, etc. ({{qualitativeanalysis.nouncat.zip| recommended qualitative evaluation criteria}})
  
-Back to the [[Start#Task 2: Categorization|the Categorization Task]] 
- 
-Back to [[Start]]