Why remove pre-trained word embedding?

jiegzhan / multi-class-text-classification-cnn-rnn

Classify Kaggle San Francisco Crime Description into 39 classes. Build the model with CNN, RNN (GRU and LSTM) and Word Embeddings on Tensorflow.

https://www.kaggle.com/c/sf-crime/data

Apache License 2.0

599 stars 262 forks source link

Open pandagod opened 7 years ago

pandagod commented 7 years ago

Hi jiegzhan,

Thanks for contributing this great project. I saw you removed pre-trained word embedding? Did it make accuracy drop down?

zxp93 commented 7 years ago

I've use pre-trained word embedding which from wiki, the score is 66.85%.