pytorch/text

Ignoring UNK words

Open

#355 aperta il 22 lug 2018

Vedi su GitHub
 (7 commenti) (0 reazioni) (0 assegnatari)Python (822 fork)batch import
enhancementhelp wanted

Metriche repository

Star
 (3396 star)
Metriche merge PR
 (Nessuna PR mergiata in 30 g)

Descrizione

Cannot find the way to ignore UNK words when numericalising, i.e. instead by substituting them by a 0, it just ignore that word.

Is that implemented?

This is useful in classification problems, when you just want to remove 'UNK' words.

Guida contributor