BARTScore
BARTScore copied to clipboard
BARTScore: Evaluating Generated Text as Text Generation
Hi, great work and really interesting approach to NLG evaluation! I was going through your implementation of computing paired bootstrap tests for estimating the significance of results and found an...
It might be wise to remove the link as it redirects to a separate website.
The evaluation scores seems to be easily affected by the selection of fine-tuned models on different datasets
How can I evaluate summaries on the BARTscore.
Hi, Could you please provide the details of Python version.
Thanks for great work! when I try to install the environment by `pip install -r requirements.txt` It will tell me that package versions have conflicting dependencies. For example, > The...