HooshvareLab/bert-fa-base-uncased-clf-persiannews

ParsBERT (v2.0) is a Transformer-based Model for Persian Language Understanding . The task target is labeling texts in a supervised manner in both existing datasets DigiMag and Persian News . The total number of articles is 16,438, spread over eight different classes . You can download the dataset from here. The following table summarizes the F1 score obtained by ParsBERt as compared to other models and architectures. The number of F1 scores is based on the number of texts labeled in the dataset. The score is: ParsBERT v1.1.0.0; F1 F1 C: C: F: P: C; C:,