问题
I have my own Fasttext model and trained with it a keras classification model with a word embedding layer.
But, I wonder how I can make use of the subword information of my model for OOV words? Since the word embedding layer operated via indices to look up word vectors and OOV words have no index. Even if a OOV token has a index how would I assign it the proper word vector to this OOV on the fly for an already trained model?
Thanks in advance!
来源:https://stackoverflow.com/questions/56043487/using-subword-information-in-oov-token-from-fasttext-in-word-embedding-layer-ke