pytorch/text

Ignoring UNK words

Open

#355 opened on Jul 22, 2018

View on GitHub
 (7 comments) (0 reactions) (0 assignees)Python (3,396 stars) (822 forks)batch import
enhancementhelp wanted

Description

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

Tech stack
python
Domain
machine learningdata
Issue type
feature
DifficultyEstimated implementation difficulty for a new contributor, from 1 for very small changes to 5 for expert-level work.
3
Estimated timeA rough time range for an experienced contributor to investigate, implement, test, and prepare a pull request.
1-3 hours
Activity statusHow available the issue appears right now: fresh, active, stale, blocked, or waiting on maintainer input.
stale
ClarityHow clearly the issue explains the expected change, acceptance criteria, and next step.
clear
Prerequisites
Python basicsPyTorch basicsNLP concepts
Newbie friendlinessA 1-100 score estimating how approachable this issue is for first-time contributors.
65
Research direction
Look into the torchtext.data.Field class, specifically the numericalize method. The current behavior substitutes unknown words with 0; we need to add an option to ignore them by filtering out UNK tokens during numericalization. Check the file torchtext/data/field.py and the related function definitions. Discuss with maintainers if there is a preferred approach (e.g., adding a parameter like 'include unk').