Using pseudowords we can overcome data sparseness problem in supervised WSD and fully verify the experimental effect of word sense classifier.
使用伪词可以避免有指导的词义消歧方法中的数据稀疏问题，充分验证词义分类器的实验效果。
2
The target words were 12 high-frequency transparent words, 12 high-frequency opaque words, 12 low-frequency transparent words, 12 low-frequency opaque words and 48 pseudowords.