ParsBERT (v2.0)
A Transformer-based Model for Persian Language Understanding
We reconstructed the vocabulary and fine-tuned the ParsBERT v1.1 on the new Persian corpora in order to provide some functionalities for using ParsBERT in other scopes! Please follow the ParsBERT repo for the latest information about previous and current models.
Persian Sentiment [Digikala, SnappFood, DeepSentiPers]
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.
SnappFood
Snappfood (an online food delivery company) user comments containing 70,000 comments with two labels (i.e. polarity classification):
- Happy
- Sad
| Label | # |
|---|---|
| Negative | 35000 |
| Positive | 35000 |
Download You can download the dataset from here
Results
The following table summarizes the F1 score obtained by ParsBERT as compared to other models and architectures.
| Dataset | ParsBERT v2 | ParsBERT v1 | mBERT | DeepSentiPers |
|---|---|---|---|---|
| SnappFood User Comments | 87.98 | 88.12* | 87.87 | - |
How to use :hugs:
| Task | Notebook |
|---|---|
| Sentiment Analysis |  |
BibTeX entry and citation info
Please cite in publications as the following:
@article{ParsBERT,
title={ParsBERT: Transformer-based Model for Persian Language Understanding},
author={Mehrdad Farahani, Mohammad Gharachorloo, Marzieh Farahani, Mohammad Manthouri},
journal={ArXiv},
year={2020},
volume={abs/2005.12515}
}
Questions?
Post a Github issue on the ParsBERT Issues repo.