pytorch/text

Ignoring UNK words

Open

#355 geöffnet am 22. Juli 2018

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

Repository-Metriken

Stars
 (3.396 Stars)
PR-Merge-Metriken
 (Keine gemergten PRs in 30 T)

Beschreibung

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.

Contributor Guide