EleanorJiang/BlonDe

Official implementations for (1) BlonDe: An Automatic Evaluation Metric for Document-level Machine Translation and (2) Discourse Centric Evaluation of Machine Translation with a Densely Annotated Parallel Corpus

47
/ 100
Emerging

This project helps evaluate the quality of document-level machine translations more accurately than traditional sentence-based metrics. It takes an original document and its machine-translated version to produce a score reflecting discourse coherence, such as correct entity tracking or pronoun usage. This tool is for machine translation researchers, language technologists, and anyone involved in assessing sophisticated translation systems.

No commits in the last 6 months. Available on PyPI.

Use this if you need to assess the quality of machine translations at the document level, specifically focusing on how well discourse elements like pronouns, tenses, and entities are handled.

Not ideal if you are only interested in evaluating translation quality at the sentence level or if your primary concern is with basic vocabulary and grammatical correctness.

machine-translation translation-quality-assessment discourse-analysis natural-language-processing computational-linguistics
Stale 6m No Dependents
Maintenance 0 / 25
Adoption 9 / 25
Maturity 25 / 25
Community 13 / 25

How are scores calculated?

Stars

83

Forks

10

Language

Python

License

MIT

Last pushed

Sep 21, 2023

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/nlp/EleanorJiang/BlonDe"

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