GitHub / StepanTita / cam-bert

We propose a novel method of fine-tuning the model for a particular downstream task, which proves to be more efficient and generalizable. We show that in an example of a fake news detection task, utilizing three distinct datasets and outperforming the baseline model in both the same dataset and cross-dataset zero-shot test.

JSON API: https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/StepanTita%2Fcam-bert

Topics: bert, covid19-data, embedding-vectors, fake-news, fake-news-detection, generalized-linear-models, kaggle-dataset, liar-dataset, natural-language-processing, nlp, politifact, transformers, zero-shot-classification

Files