awslabs/mlm-scoring

Python library & examples for Masked Language Model Scoring (ACL 2020)

47
/ 100
Emerging

This tool helps improve the accuracy of language processing tasks like speech recognition and machine translation. It takes text inputs, or lists of possible transcriptions/translations, and uses advanced language models (like BERT or GPT-2) to assign a "linguistic quality" score. This score helps you pick the most natural-sounding or grammatically correct option, making the final output more reliable for professionals working with large volumes of text or audio data.

348 stars. No commits in the last 6 months.

Use this if you need to rank or select the most grammatically acceptable or natural-sounding sentences from a list of options generated by another system, such as in speech recognition or machine translation.

Not ideal if you're looking for a tool to generate text from scratch or to perform semantic analysis beyond simple sentence scoring.

Speech Recognition Machine Translation Natural Language Processing Linguistic Acceptability Content Quality
Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 10 / 25
Maturity 16 / 25
Community 21 / 25

How are scores calculated?

Stars

348

Forks

60

Language

Python

License

Apache-2.0

Last pushed

Dec 20, 2022

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/transformers/awslabs/mlm-scoring"

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