You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
Thank you for sharing wonderful ideas and the code repository for improving the factual consistency of summarization.
I had a question regarding the code base. I am wondering if the repository also includes the code to fine-tune CONSEQ model using constrastive loss? As far as I can tell, the repo only includes code to preprocess the dataset into positive and negative samples. Please correct me if I am wrong. Appreciate your time and response. Thank you!
The text was updated successfully, but these errors were encountered:
Thanks for pointing out. Finetuning code is in scripts/launch_sagemaker_unlikelihood_cnndm.py and scripts/launch_sagemaker_unlikelihood_xsum.py. Fixed the README.
Hi,
Thank you for sharing wonderful ideas and the code repository for improving the factual consistency of summarization.
I had a question regarding the code base. I am wondering if the repository also includes the code to fine-tune CONSEQ model using constrastive loss? As far as I can tell, the repo only includes code to preprocess the dataset into positive and negative samples. Please correct me if I am wrong. Appreciate your time and response. Thank you!
The text was updated successfully, but these errors were encountered: