Effect of the training set on the word embeddings and similarity test set for Turkish.
Veysel YücesoyAykut KoçPublished in: SIU (2016)
Keyphrases
- test set
- training set
- test data
- error rate
- distance measure
- training data
- similarity measure
- data sets
- class distribution
- co occurrence
- test cases
- decision trees
- evaluation methodology
- word pairs
- cross validation
- low dimensional
- active learning
- training samples
- nearest neighbor
- vector space
- classification error
- classification accuracy
- support vector