OpenNMT / OpenNMT/CTranslate2

NLLB translation mask or skip some tokens

Open
#1,798 0 comments 0 reactions 0 assignees View on GitHub

Nobody has claimed this yet.

Dominant language
C++
Stars
4.7k
Forks
536
Avg merge
12h 12m
Merged PRs (30d)
4

Description

İs there a way to skip some words in translation,I jus want to get the input in the same way at my result (ofc since gramattical differences the order will change but I need to get the exact words in output) I tried to wrap some words with some placeholders $$$skipping words$$, I also tried to creat enumerated placeholders so that i can change them after translation (1_1_1, <1>,<2>,....). I also tried to give numbers. directly Like 11111111, 11111112, ... but None of them worked. Did someone try to do similar think?
Thnx in advance

Contributor guide

Open the contributing guide

First steps

  1. Read the whole issue, then the project's contributing guide.
  2. Comment on the issue to say you are picking it up — it saves two people doing the same work.
  3. Fork the repository and make your change on a branch.
  4. Open a pull request that references the issue number.

Research direction

The issue does not name a file, test, or entry point. Start by reproducing the reported placeholder and token-skipping attempts with NLLB translation, then identify the relevant translation or tokenization entry point. Done means establishing a supported way to preserve selected input words in the output.

Written by the indexing model from the issue text.

Assessment

Tech stack
cpp
Domain
machine-learning
Issue type
Feature
Difficulty
5/5
Estimated time
Over a week
Activity status
Stale
Clarity
Needs clarification
Newbie friendliness
25/100

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.