DistilBERT Base Multilingual Cased Fine-Tuned CONLL2003 NER Open-Source Model - Supports Multilingual Named Entity Recognition

Distilbert Base Multilingual Cased Finetuned Conll2003 Ner

Developed by gunghio

This is a multilingual model based on DistilBERT, specifically fine-tuned for named entity recognition tasks on the CoNLL 2003 dataset.

Sequence Labeling

Transformers

Supports Multiple Languages#Multilingual NER #High-precision entity recognition #CoNLL2003 optimization

Downloads 73

Release Time : 3/2/2022

Model Overview

This model is a named entity recognition model based on the distilbert-base-multilingual-cased architecture, supporting entity recognition tasks in multiple languages such as English, German, Dutch, and Spanish.

Model Features

Multilingual Support

Supports named entity recognition in multiple languages including English, German, Dutch, and Spanish

Efficient Model

Based on the DistilBERT architecture, it reduces model size and computational requirements while maintaining performance

High Accuracy

Achieved an excellent F1 score of 0.9409 on the CoNLL 2003 dataset

Model Capabilities

Named Entity Recognition

Multilingual Text Processing

Entity Classification

Use Cases

Information Extraction

News Article Entity Extraction

Identify entities such as person names, locations, and organization names from news articles

99.02% accuracy

Multilingual Document Processing

Handle entity recognition tasks in multilingual mixed documents

🚀 gunghio/distilbert-base-multilingual-cased-finetuned-conll2003-ner

This model is trained from scratch on the conll2003 dataset and achieves high performance in Named Entity Recognition tasks.

🚀 Quick Start

This model was trained from scratch on an conll2003 dataset. It achieves the following results on the evaluation set:

Loss: 0.0388
Precision: 0.9360
Recall: 0.9458
F1: 0.9409
Accuracy: 0.9902

✨ Features

High Performance: Achieves excellent results on the evaluation set, including high precision, recall, F1-score, and accuracy.
Multilingual Support: Supports multiple languages such as English (en), German (de), Dutch (nl), Spanish (es), and multilingual scenarios.

📦 Installation

No specific installation steps are provided in the original document.

💻 Usage Examples

No code examples are provided in the original document.

📚 Documentation

Model description

It is based on distilbert-base-multilingual-cased.

Intended uses & limitations

More information needed.

Training and evaluation data

Training dataset: conll2003

Training procedure

Training hyperparameters

The following hyperparameters were used during training:

learning_rate: 2e-05
train_batch_size: 16
eval_batch_size: 16
seed: 42
optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
lr_scheduler_type: linear
num_epochs: 3

Training results

Training Loss	Epoch	Step	Validation Loss	Precision	Recall	F1	Accuracy
0.1653	1.0	878	0.0465	0.9267	0.9300	0.9283	0.9883
0.0322	2.0	1756	0.0404	0.9360	0.9431	0.9396	0.9897
0.0185	3.0	2634	0.0388	0.9360	0.9458	0.9409	0.9902

Framework versions

Transformers 4.6.1
Pytorch 1.8.1+cu101
Datasets 1.6.2
Tokenizers 0.10.2

🔧 Technical Details

Metrics

Property	Details
Precision	0.936
Recall	0.9458
F1	0.9409
Accuracy	0.9902

Datasets

conll2003

Languages

en
de
nl
es
multilingual

Model Index

Name: gunghio/distilbert-base-multilingual-cased-finetuned-conll2003-ner
- Results:
  - Task:
    - Type: ner
    - Name: Named Entity Recognition
  - Dataset:
    - Type: conll2003
    - Name: ConLL 2003
  - Metrics:
    - Type: f1-score
    - Value: 0.9409

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