pytorch/text

Ignoring UNK words

Open

#355 建立於 2018年7月22日

在 GitHub 查看
 (7 留言) (0 反應) (0 負責人)Python (822 fork)batch import
enhancementhelp wanted

倉庫指標

Star
 (3,396 star)
PR 合併指標
 (30 天內沒有已合併 PR)

描述

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.

貢獻者指南