README.md

metadata

library_name: transformers
tags: []

Model Card for Model ID

BERT NER Model (CoNLL-2003)

📌 Overview

This model is a fine-tuned version of bert-base-cased for the task of Named Entity Recognition (NER).

🎯 Task

Token Classification (Named Entity Recognition)

The model identifies the following entity types:

• PER (Person)
• ORG (Organization)
• LOC (Location)
• MISC (Miscellaneous)

📊 Dataset

• CoNLL-2003 (English news dataset)
• Only NER tags were used (BIO format)

🧠 Model Details

• Base model: bert-base-cased
• Architecture: Transformer Encoder (BERT)
• Fine-tuning: Hugging Face Transformers
• Training epochs: 3

📈 Performance

Test set results:

• Precision: ~0.90
• Recall: ~0.91
• F1-score: ~0.91
• Accuracy: ~0.98

⚙️ Usage Example

from transformers import pipeline

ner = pipeline(
    "ner",
    model="x4n4/bert-conll2003-ner",
    aggregation_strategy="simple"
)

text = "Barack Obama visited Google in New York"
print(ner(text))