bert-fa-base-uncased-ner-peyma Open-source Persian Language Understanding Model - Refactoring the Vocabulary to Expand Multi-domain Application Functions

Bert Fa Base Uncased Ner Peyma

Developed by HooshvareLab

A Transformer-based Persian language understanding model, reconstructed vocabulary and fine-tuned on new corpora, expanding multi-domain application capabilities

Sequence Labeling OtherOpen Source License:Apache-2.0 #Persian NER #Multi-category Entity Recognition #Transformer Architecture

Downloads 69.74k

Release Time : 3/2/2022

Model Overview

ParsBERT is a BERT model specifically optimized for Persian, primarily used for Named Entity Recognition (NER) tasks, capable of identifying entities such as person names, locations, and organizations in text

Model Features

Optimized Vocabulary

Reconstructed vocabulary to better adapt to Persian language characteristics

Multi-domain Adaptability

Fine-tuned on new corpora, expanding the model's application capabilities across different domains

High-performance NER

Achieved an F1 score of 93.4 on Persian NER tasks, outperforming other similar models

Model Capabilities

Persian text understanding

Named Entity Recognition

Multi-category token classification

Use Cases

Information Extraction

Organization Identification

Identify company and government agency names from Persian documents

F1 score 93.4

Geographic Information Extraction

Identify geographic location information in text

F1 score 93.4

Financial Analysis

Monetary Amount Recognition

Extract monetary amount information from financial reports

🚀 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 enable ParsBERT for use 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 and its applications.

✨ Features

Persian NER [ARMAN, PEYMA]

This task focuses on extracting named entities from text, such as names, and labeling them with appropriate NER classes like locations, organizations, etc. The datasets used for this task contain sentences marked in the IOB format. In this format, tokens not part of an entity are tagged as "O", the "B" tag represents the first word of an entity, and the "I" tag represents the remaining words of the same entity. Both "B" and "I" tags are followed by a hyphen (or underscore), then the entity category. Thus, the NER task is a multi-class token classification problem that labels tokens given raw text. There are two main datasets used in Persian NER: ARMAN and PEYMA.

PEYMA

The PEYMA dataset consists of 7,145 sentences with a total of 302,530 tokens, of which 41,148 tokens are tagged with seven different classes:

Organization
Money
Location
Date
Time
Person
Percent

Label	#
Organization	16964
Money	2037
Location	8782
Date	4259
Time	732
Person	7675
Percent	699

Download You can download the dataset from here

📚 Documentation

Results

The following table summarizes the F1 score achieved by ParsBERT compared to other models and architectures.

Dataset	ParsBERT v2	ParsBERT v1	mBERT	MorphoBERT	Beheshti-NER	LSTM-CRF	Rule-Based CRF	BiLSTM-CRF
PEYMA	93.40*	93.10	86.64	-	90.59	-	84.00	-

How to use :hugs:

Notebook	Description
How to use Pipelines	A simple and efficient way to use State-of-the-Art models on downstream tasks through transformers

📄 License

This project is licensed under the Apache-2.0 license.

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}
}

💡 Usage Tip

If you have any questions, post a Github issue on the ParsBERT Issues repository.

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