FrankWork / conv_relation

TensorFlow implementation of Relation Classification via Convolutional Deep Neural Network
94 stars 29 forks source link

Testing on a new test set generate an error #12

Closed Hadjerkhd closed 5 years ago

Hadjerkhd commented 5 years ago

I changed the code to do the validation on a dev set instead of the test set. But when I wanted to test the model on my test set, i got an error when mapping words_to_ids (reader/base.py), this is due to the fact that the vocab.txt file was constructed only on the train and dev data. Do I need to use three of the train, dev and test sets to construct this vocab.txt file ?
Wouldn't this be a heavy constraint when using the model to predict on new data that we don't know its vocabulary in advance ? Thanks for your answer in advance.