yashpwr/resume-ner-bert

Resume NER Model

A fine-tuned BERT model for Named Entity Recognition (NER) specifically designed for resume/CV parsing and information extraction.

Model Description

This model is based on bert-base-cased and has been fine-tuned to extract key information from resume documents including:

• label_to_id
• id_to_label

Performance

Metric	Score
F1 Score	0.7128521806252412
Precision	0.6843275287143387
Recall	0.7438582360048329
Accuracy	0.9482567433286769

Usage

from transformers import pipeline

# Load the model
ner_pipeline = pipeline(
    "ner", 
    model="yashpwr/resume-ner-bert",
    aggregation_strategy="simple"
)

# Extract entities from resume text
text = "John Doe is a Software Engineer at Google. Email: [email protected]"
results = ner_pipeline(text)

for entity in results:
    print(f"{entity['word']}: {entity['entity_group']} ({entity['score']:.3f})")

Training Data

• Training samples: 576
• Validation samples: 144
• Epochs: 3

Intended Use

This model is designed for:

• Resume parsing systems
• HR automation tools
• Recruitment platforms
• Document processing pipelines

Limitations

• Optimized specifically for resume/CV documents
• Performance may vary on other document types
• Requires preprocessing for best results

Model Details

• Base model: bert-base-cased
• Model size: ~110M parameters
• Language: English
• License: Apache 2.0