pytorch/text

Vocab vectors using complete pretrained-embedding?

Open

#446 geöffnet am 12. Okt. 2018

Auf GitHub ansehen
 (6 Kommentare) (0 Reaktionen) (0 zugewiesene Personen)Python (3.396 Stars) (822 Forks)batch import
enhancementhelp wanted

Beschreibung

I am new to pytorch and nlp. I have a question when I tried to build a model.

Since my training dataset is not so big, the size of its vocab is relatively small (around 5000). However, I want to deal with any other user input which could be out of this vocabulary.

The problem is, in the model I trained, the embedding layer's weight is based on the vectors of the field, not the whole word2vec pretrained embeddings. So I cannot modified it after the training is done.

I wondered is there any better approach to do it? Thanks in advance!

Contributor Guide