This model is a fine-tuned version of google-bert/bert-base-uncased for Named Entity Recognition (NER) using the CoNLL-2003 dataset. The model classifies tokens into named entity categories such as persons, locations, organizations, and miscellaneous entities.

Developed by: Gowtham Arulmozhi
Language(s) (NLP): English (en)
License: MIT
Finetuned from model : google-bert/bert-base-uncased

How to Get Started with the Model

Run this snippet to use the model with 🤗 Transformers:

python

from transformers import pipeline

ner_pipeline = pipeline("ner", model="Wothmag07/NER-fine-tuned-model")
text = "Barack Obama was born in Hawaii."
results = ner_pipeline(text)
print(results)

Training Details

Training Data

The model was trained using the CoNLL-2003 dataset, which contains news articles annotated for named entities.

Training Hyperparameters

Batch size: 16
Learning rate: 2e-5
Epochs: 20
Optimizer: Adam

Evaluation

Tested on CoNLL-2003 test set with:

Accuracy: 0.987084
F1-score: 0.947727
Precision: 0.945248
Recall: 0.950218