BERT-FA-ZWNJ-Base-NER Open Source Model - Free Deployment, Supports 10 Types of Entity Recognition in Persian

Bert Fa Zwnj Base Ner

Developed by HooshvareLab

A BERT model fine-tuned for Persian Named Entity Recognition (NER) tasks, supporting 10 entity categories

Sequence Labeling Other#Persian Named Entity Recognition #Multi-source Data Training #Ten Entity Categories Annotation

Downloads 6,189

Release Time : 3/2/2022

Model Overview

This model is based on the BERT architecture and fine-tuned for Persian Named Entity Recognition tasks. It can identify ten types of entities including dates, events, facilities, locations, monetary values, organizations, percentages, persons, products, and time expressions.

Model Features

Multi-source Dataset Training

Trained on a combination of three Persian NER datasets: ARMAN, PEYMA, and WikiANN

Ten Entity Categories Recognition

Supports recognition of ten entity categories including dates, events, facilities, locations, monetary values, organizations, percentages, persons, products, and time expressions

High-precision Performance

Achieves an overall F1 score of 0.957 on the test set, with most entity categories exceeding 0.95 F1 score

Model Capabilities

Persian text processing

Named Entity Recognition

Entity classification

Use Cases

Text Analysis

News Entity Extraction

Extract key entities such as persons, organizations, and locations from Persian news

Accurately identifies key information in news articles

Financial Document Analysis

Analyze monetary values, percentages and other entities in Persian financial documents

Assists in financial data extraction and analysis

Information Retrieval

Knowledge Graph Construction

Extract entities from Persian texts for knowledge graph construction

Improves knowledge graph construction efficiency

🚀 BertNER

This model is fine - tuned for the Named Entity Recognition (NER) task. It uses a mixed NER dataset collected from ARMAN, PEYMA, and WikiANN. The dataset covers ten types of entities:

Date (DAT)
Event (EVE)
Facility (FAC)
Location (LOC)
Money (MON)
Organization (ORG)
Percent (PCT)
Person (PER)
Product (PRO)
Time (TIM)

✨ Features

Fine - tuned for NER task on a comprehensive mixed dataset.
Covers ten different types of entities.

📦 Installation

Installing requirements

pip install transformers

💻 Usage Examples

Basic Usage

from transformers import AutoTokenizer
from transformers import AutoModelForTokenClassification  # for pytorch
from transformers import TFAutoModelForTokenClassification  # for tensorflow
from transformers import pipeline


model_name_or_path = "HooshvareLab/bert-fa-zwnj-base-ner" 
tokenizer = AutoTokenizer.from_pretrained(model_name_or_path)
model = AutoModelForTokenClassification.from_pretrained(model_name_or_path)  # Pytorch
# model = TFAutoModelForTokenClassification.from_pretrained(model_name_or_path)  # Tensorflow

nlp = pipeline("ner", model=model, tokenizer=tokenizer)
example = "در سال ۲۰۱۳ درگذشت و آندرتیکر و کین برای او مراسم یادبود گرفتند."

ner_results = nlp(example)
print(ner_results)

📚 Documentation

Dataset Information

Property	Details
Model Type	BertNER fine - tuned for NER
Training Data	Mixed dataset from ARMAN, PEYMA, and WikiANN

	Records	B-DAT	B-EVE	B-FAC	B-LOC	B-MON	B-ORG	B-PCT	B-PER	B-PRO	B-TIM	I-DAT	I-EVE	I-FAC	I-LOC	I-MON	I-ORG	I-PCT	I-PER	I-PRO	I-TIM
Train	29133	1423	1487	1400	13919	417	15926	355	12347	1855	150	1947	5018	2421	4118	1059	19579	573	7699	1914	332
Valid	5142	267	253	250	2362	100	2651	64	2173	317	19	373	799	387	717	270	3260	101	1382	303	35
Test	6049	407	256	248	2886	98	3216	94	2646	318	43	568	888	408	858	263	3967	141	1707	296	78

Evaluation

The following tables summarize the scores obtained by model overall and per each class.

Overall

Model	accuracy	precision	recall	f1
Bert	0.995086	0.953454	0.961113	0.957268

Per entities

	number	precision	recall	f1
DAT	407	0.860636	0.864865	0.862745
EVE	256	0.969582	0.996094	0.982659
FAC	248	0.976190	0.991935	0.984000
LOC	2884	0.970232	0.971914	0.971072
MON	98	0.905263	0.877551	0.891192
ORG	3216	0.939125	0.954602	0.946800
PCT	94	1.000000	0.968085	0.983784
PER	2645	0.965244	0.965974	0.965608
PRO	318	0.981481	1.000000	0.990654
TIM	43	0.692308	0.837209	0.757895

❓ Questions

Post a Github issue on the ParsNER Issues repo.

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