SriramRokkam/BERT_NER

---

BERT Named Entity Recognition (NER) Model

This model performs Named Entity Recognition (NER) using a fine-tuned version of BERT (Bidirectional Encoder Representations from Transformers) based on the bert-base-cased model from Google. It identifies entities in a given text, such as people, organizations, and locations. The model has been fine-tuned on a custom NER dataset.

---

Model Overview

• Model: BERT-based NER
• Base model: bert-base-cased
• Language: English (en)
• Task: Text Classification (NER)

---

Dataset

The dataset used for training is available here.

---

Metrics

This model has been evaluated on various metrics:

• Evaluation Loss: 0.176
• Precision: 82.5%
• Recall: 77.1%
• F1 Score: 79.7%
• Accuracy: Reported during evaluation.

---

Usage

You can use this model in two ways: via direct code execution or by running a Docker container.

Option 1: Direct Code Execution

To use this model via code, you’ll first need to log in to Hugging Face CLI and enter your access token.

Step 1: Install Hugging Face Transformers and CLI

If you haven’t already, install the necessary dependencies:

pip install transformers huggingface_hub

Step 2: Login to Hugging Face

Use the following command to log in to your Hugging Face account:

huggingface-cli login

You'll be prompted to enter your Hugging Face access token. You can find your token here.

Step 3: Use the Model

Once logged in, you can use the following Python code to load and run the model for NER tasks:

from transformers import AutoTokenizer, AutoModelForTokenClassification, pipeline

# Load the model and tokenizer
model_name = "sriramrokkam/bert_ner"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModelForTokenClassification.from_pretrained(model_name)

# Create a pipeline for NER
nlp = pipeline("ner", model=model, tokenizer=tokenizer)

# Interactive example
input_text = input("Enter a sentence for NER: ")
ner_results = nlp(input_text)

# Display results
for entity in ner_results:
    print(f"Entity: {entity['word']}, Label: {entity['entity']}, Confidence: {entity['score']:.2f}")

---

Option 2: Docker

You can also run this model using Docker for a simple and interactive NER chatbot interface.

Prerequisites

Make sure you have Docker installed on your system.

Step 1: Pull the Docker Image

Pull the Docker image from Docker Hub:

docker pull sriramrokkam/ner-chatbot-web

View on Docker Hub

Step 2: Run the Docker Container

Run the container to start the web-based NER chatbot interface:

docker run -p 8080:8080 --name BERT_NER_Chatbot -it sriramrokkam/ner-chatbot-web

Step 3: Access the Web Interface

Once the container is running, open your browser and go to:

http://localhost:8080

This will open a professional chatbot interface where you can enter text, and the model will perform Named Entity Recognition (NER) on the input.

---

License

This project is licensed under the MIT License.

---

Contact Information

• Author: Sriram Rokkam
• GitHub: BERT_NER GitHub
• LinkedIn: Sriram Rokkam
• Email: sriramrokkam@gmail.com
• Docker Hub: Sriram Rokkam

---