A Lite BERT for Self-supervised Learning of Language Representations for the Persian Language

ALBERT-Persian is the first attempt on ALBERT for the Persian Language. The model was trained based on Google's ALBERT BASE Version 2.0 over various writing styles from numerous subjects (e.g., scientific, novels, news) with more than 3.9M documents, 73M sentences, and 1.3B words, like the way we did for ParsBERT.

Please follow the ALBERT-Persian repo for the latest information about previous and current models.

It aims to classify text, such as comments, based on their emotional bias. We tested three well-known datasets for this task: Digikala user comments, SnappFood user comments, and DeepSentiPers in two binary-form and multi-form types.

Digikala user comments provided by Open Data Mining Program (ODMP). This dataset contains 62,321 user comments with three labels:

Download You can download the dataset from here

The following table summarizes the F1 score obtained as compared to other models and architectures.

Please cite in publications as the following:

Post a Github issue on the ALBERT-Persian repo.