Bert Addresses

🚀 Model Card for Model ID

This model is designed for tagging names, organizations, and addresses, leveraging a combined dataset for enhanced performance.

🚀 Quick Start

Direct Use

from transformers import AutoTokenizer, AutoModelForTokenClassification
from transformers import pipeline
tokenizer = AutoTokenizer.from_pretrained('bert-base-cased')
model = AutoModelForTokenClassification.from_pretrained("ctrlbuzz/bert-addresses")
nlp = pipeline("ner", model=model, tokenizer=tokenizer)
example = "While Maria was representing Johnson & Associates at a conference in Spain, she mailed me a letter from her new office at 123 Elm St., Apt. 4B, Springfield, IL.",

print(nlp(example))

✨ Features

This model can tag names, organizations, and addresses. It uses a combined dataset from Conll, ontonotes5, and a custom - made address dataset. It has cleaned tags and can detect U.S. addresses. The tag set includes ["O", "B - ORG", "I - ORG", "B - PER", "I - PER", 'B - addr', 'I - addr'].

📚 Documentation

Model Description

For reference on model card metadata, see the spec: https://github.com/huggingface/hub-docs/blob/main/modelcard.md?plain=1 Doc / guide: https://huggingface.co/docs/hub/model - cards