sumeval
Well tested & Multi-language evaluation framework for text summarization.
- 626
- Python
- Apache-2.0
- 7 mo ago
Well tested & Multi-language evaluation framework for text summarization.
ROUGE automatic summarization evaluation toolkit. Support for ROUGE-[N, L, S, SU], stemming and stopwords in different languages, unicode text evaluation, CSV output.
Domain-specific adaptation of CodeT5 for Python docstring generation. Compares pre-trained vs fine-tuned performance using NLP metrics (ROUGE, METEOR, BERTScore), showing significant improvements after targeted training.
Utility tools to prepare and evaluate ROUGE scores. Perl script to convert perl output of ROUGE to CSV.