Skip to Main Content

The ADN-Classifier therefore consists of the J48.Part classifier within the Weka toolbox, the appropriate learned model (from the set described in Section 7.2 and listed in Table 5), and the list of features to be used. During the exploitation phase the input to the system consists of a table. Each row in the table corresponds to a case for classifying and each column to the values of the corresponding feature. The result of the process is a column vector containing the result of classifying each instance.

Table 5

Experiments and evaluation of the models. Legend of the model name: 1st letter (S = sense-based, L = lemma-based); 2nd letter (S = sense, L = lemma, E = corpus example); 3rd letter (L = lexicon features, C = corpus features, A = all features); 4th letter (R = reduced vocabulary, F = full vocabulary) and 5th letter (R = reduced corpus, F = full corpus).

graphic
 
graphic
 

Close Modal

or Create an Account

Close Modal
Close Modal