alphadl/EasyBLEU
An effective and simple tool to calculate SacreBLEU, Token-BLEU, BLEU w/ compound splitting for fairseq
This tool helps machine translation researchers fairly compare the quality of different translation systems. You input a test dataset, the source and target languages, and your system's generated translations. It then outputs standard BLEU scores like SacreBLEU, Token-BLEU, and BLEU with compound splitting, which are essential for evaluating translation performance. This is for researchers in the field of natural language processing and machine translation.
No commits in the last 6 months.
Use this if you are developing or evaluating machine translation models, especially within the fairseq framework, and need a standardized way to calculate BLEU scores.
Not ideal if you are not working on machine translation or if you need to evaluate translation quality using metrics other than BLEU.
Stars
7
Forks
1
Language
Shell
License
—
Category
Last pushed
Sep 23, 2020
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/nlp/alphadl/EasyBLEU"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
google/langfun
OO for LLMs
tanaos/artifex
Small Language Model Inference, Fine-Tuning and Observability. No GPU, no labeled data needed.
preligens-lab/textnoisr
Adding random noise to a text dataset, and controlling very accurately the quality of the result
vulnerability-lookup/VulnTrain
A tool to generate datasets and models based on vulnerabilities descriptions from @Vulnerability-Lookup.
masakhane-io/masakhane-mt
Machine Translation for Africa