bert-fa-base-uncased Open-source Persian Language Comprehension Model

Bert Fa Base Uncased Sentiment Deepsentipers Binary

Developed by HooshvareLab

A Transformer-based Persian language understanding model, with a reconstructed vocabulary and fine-tuned on a new Persian corpus, suitable for various Persian NLP tasks.

Text Classification OtherOpen Source License:Apache-2.0 #Persian Sentiment Analysis #Multi-class Sentiment Recognition #Transformer Architecture

Downloads 28.50k

Release Time : 3/2/2022

Model Overview

ParsBERT is a Transformer-based Persian language understanding model, primarily used for natural language processing tasks such as sentiment analysis in Persian text.

Model Features

Optimized Persian Vocabulary

Reconstructed vocabulary and fine-tuned on a new Persian corpus, enhancing model performance.

Multi-sentiment Classification Capability

Supports binary and multi-class sentiment analysis, capable of recognizing emotions ranging from anger to joy.

Multi-dataset Support

Performs excellently on multiple Persian datasets including Digikala, SnappFood, and DeepSentiPers.

Model Capabilities

Persian text understanding

Sentiment analysis

Multi-class task processing

Use Cases

Sentiment Analysis

E-commerce Review Sentiment Analysis

Analyze user review sentiment tendencies on e-commerce platforms like Digikala

F1 score of 92.42% (binary classification)

Restaurant Review Sentiment Analysis

Analyze user review sentiment tendencies on food delivery platforms like SnappFood

Digital Product Review Analysis

Multi-sentiment classification of digital product reviews in the DeepSentiPers dataset

F1 score of 71.31% (multi-class)

🚀 ParsBERT (v2.0)

A Transformer-based Model for Persian Language Understanding

We reconstructed the vocabulary and fine-tuned ParsBERT v1.1 on new Persian corpora to offer additional functionalities for using ParsBERT in other scenarios. For the latest information on previous and current models, please follow the ParsBERT repository.

🚀 Quick Start

This section provides an overview of ParsBERT's capabilities and how it can be used in different tasks.

✨ Features

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.

DeepSentiPers

DeepSentiPers, a balanced and augmented version of SentiPers, contains 12,138 user opinions about digital products labeled with five different classes: two positives (i.e., happy and delighted), two negatives (i.e., furious and angry), and one neutral class. Thus, this dataset can be used for both multi - class and binary classification. In binary classification, the neutral class and its corresponding sentences are removed from the dataset.

Binary:

Negative (Furious + Angry)
Positive (Happy + Delighted)

Multi

Furious
Angry
Neutral
Happy
Delighted

Label	#
Furious	236
Angry	1357
Neutral	2874
Happy	2848
Delighted	2516

Download You can download the dataset from:

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
SentiPers (Multi Class)	71.31*	71.11	-	69.33
SentiPers (Binary Class)	92.42*	92.13	-	91.98

💻 Usage Examples

Task	Notebook
Sentiment Analysis

📚 Documentation

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.

📄 License

This project is licensed under the Apache 2.0 license.

Featured Recommended AI Models

Empowering the Future, Your AI Solution Knowledge Base

English 简体中文繁體中文にほんご