@article{Beltagy2020Longformer, title={Longformer: The Long-Document Transformer}, author={Iz Beltagy and Matthew E. Peters and Arman Cohan}, journal={arXiv:2004.05150}, year={2020}, }
Dataset: Retrieved from kaggle: https://www.kaggle.com/datasets/clmentbisaillon/fake-and-real-news-dataset?select=Fake.csv
This model is fine-tuned on Longformer 4096 with political and world news from 2016 to 2018, so it will probably identify all current news as fake since the world has changed a lot since then
But it performs well on more related news article: Test accuracy: 0.9956 val_loss: 0.0003
- Downloads last month
- 6