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:verb_categorization [2008/01/20 16:07]
alexlenci 		— (current)
Line 1: Line 1:
-====== Task 1.c - Verb Categorization ====== 
- 
-==== Introduction ==== 
- 
-The goal of the sub-task is to group verbs into semantic categories. 
- 
-The {{verb.categorization.dataset.tar.gz |data set}} consists of 45 verbs, belonging to 9 semantic classes. The classification scheme is inspired to the one described in P. Vinson & G. Vigliocco (2007), “Semantic Feature Production Norms for a Large Set of Objects and Events”, //Behavior Research Methods//, which in turn closely follows the classification proposed in Levin (1993). 
- 
-==== Task Operationalization ==== 
- 
-We operationalize verb categorization as a clustering task. Since the data set is organized hierarchically, 
-we will run two clustering experiments, varying the number of classes and consequently their level of generality: 
- 
-  * **9-way clustering** - models will be tested on their ability to categorize the verbs into the most fine-grained classes of the dataset: //communication// ("talk"), //mentalState// ("know"), //motionManner// ("run"), //motionDirection// ("arrive"), //changeLocation// ("carry"), //bodySense// ("smell"), //bodyAction// ("eat"), //exchange// ("buy"), //changeState// ("destroy"); 
-  * **5-way clustering** - models will be tested on their ability to categorize the verbs into 5 classes: //cognition// (superordinate of //communication// and //mentalState//), //motion// (superordinate of //motionManner//, //motionDirection//, //changeLocation//), //body// (superordinate of //bodySense// and //bodyAction//), //exchange//, and //changeState//; 
- 
-To abstract away from differences stemming from any specific clustering method, you are asked to run your experiments with the //k-means// algorithm available in [[http://glaros.dtc.umn.edu/gkhome/cluto/cluto/overview|CLUTO]]. In case you can not run  [[http://glaros.dtc.umn.edu/gkhome/cluto/cluto/overview|CLUTO]] on your system, the workshop organizers will carry out the clustering for you. In this case, data should be prepared according to a format that will be specified later on. Participants are also invited to experiment with other clustering methods and to compare the results with those obtained with[[http://glaros.dtc.umn.edu/gkhome/cluto/cluto/overview|CLUTO]]. 
- 
- 
-==== Task Evaluation ==== 
- 
-Evaluation will be carried in two stages: 
- 
-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** - verb semantic classification is notoriously hard. Any a priori classification scheme runs the risk of being defied by the highly polysemous and multidimensional semantic character of verbs. In this second stage, evaluatio will therefore focus on specific verbs selected as "hard cases" or as particularly excentric member of thier classes. Participants will be asked to perform a fine-grained error analysis behavor with thes eselected verbs. Details about this type of evaluation will be provided later on. 
- 
-Back to [[Start]] 
- 
  

You are here: start » data » verb_categorization