nlg-eval
This repository offers code to evaluate unsupervised metrics in Natural Language Generation. It processes hypothesis and reference inputs to compute various metrics like BLEU, ROUGE, and CIDEr. Java and Python dependencies are needed for installation, and it can be used via command line or Python API. It supports assessments of both individual and multiple examples, providing flexibility for research applications. Users can customize settings for metrics like CIDEr to enhance precision.
