2022 •
Saved Weights of Best Frozen Models for FETILDA on the US Bank Dataset
Authors: Bolun \\"Namir\\" Xia, Rawte, Vipula D., Gupta, Aparna, Zaki, Mohammed J.
Venue: Zenodo
Type: Other
Abstract: These six zipped folders contain the saved weights of the best frozen model for FETILDA (w/BERT, w/FinBERT, and w/Longformer) obtained from experimenting on the US Bank dataset that we collected, which contains 10-K reports submitted by US banks from 2006 to 2016. Three of the six zipped folders contain weights obtained using historical scores as features in training FETILDA, and the other three contain weights obtained without doing so. They are clearly labeled in the names of the folders and files. The files are in the PyTorch .pt format.
We have placed cookies on your device to help make this website and the services we offer better. By using this site, you agree to the use of cookies. Learn more