chenllliang/MLS

Source code of our paper "Focus on the Target’s Vocabulary: Masked Label Smoothing for Machine Translation" @ACL-2022

29
/ 100
Experimental

This project offers a refined approach to improve the accuracy of machine translation systems. By optimizing how translation models handle vocabulary between different languages, it takes text in one language and produces a more precise translation in another. This is for researchers and engineers developing new machine translation models or enhancing existing ones.

No commits in the last 6 months.

Use this if you are developing or fine-tuning neural machine translation models and want to enhance translation quality and model calibration.

Not ideal if you are looking for an off-the-shelf translation tool for everyday use or are not familiar with machine learning model development.

neural-machine-translation natural-language-processing computational-linguistics AI-research language-AI-development
No License Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 6 / 25
Maturity 8 / 25
Community 15 / 25

How are scores calculated?

Stars

18

Forks

4

Language

Python

License

Last pushed

May 19, 2022

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/nlp/chenllliang/MLS"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.