search

yoonkim / CNN_sentence

CNNs for sentence classification
2.05k stars 827 forks source link

Dealing with unknown words #29

Closed igorbpf closed 7 years ago

igorbpf commented 7 years ago

Does anyone know how words present in dataset, but absent in pre-trained word2vec embedding were treated? In the paper is not clear.

yoonkim commented 7 years ago

they were initialized randomly with a uniform distribution with support [-0.25, 0.25]

igorbpf commented 7 years ago

Sure! It is present in the section 3.2! My bad! Thank u very much!