Closed HarlynDN closed 3 months ago
Hello @HarlynDN and thank you for your message.
I've just pushed to the repo our annotation data (200 samples), and the accompanying notebook (Eval_Benchmarking.ipynb) that should help reproduce the experiment.
Excited to see what you cook up to try to improve the eval strategies :)
Philippe
Thank you for the update :)
Hi,
Thank you for this awesome work! Are you planning to release the human-annotated summaries and evaluation script to run the experiments in Table 1 of your paper? I am interested in further testing additional models and evaluation strategies.