Roberta Ticker

🚀 roberta-ticker: Detect Financial Tickers with Fine-tuned Roberta

This model is fine-tuned from Roberta to detect financial tickers in text, offering a reliable solution for financial text analysis.

🚀 Quick Start

✨ Features

• Specifically designed to identify tickers in text.
• Trained on a transformed dataset from a Kaggle source.

📦 Installation

No specific installation steps are provided in the original document, so this section is skipped.

💻 Usage Examples

Basic Usage

# Load roberta-ticker and its sub-word tokenizer
from transformers import AutoTokenizer, AutoModelForTokenClassification

tokenizer = AutoTokenizer.from_pretrained("Jean-Baptiste/roberta-ticker")
model = AutoModelForTokenClassification.from_pretrained("Jean-Baptiste/roberta-ticker")

# Process text sample
from transformers import pipeline

nlp = pipeline('ner', model=model, tokenizer=tokenizer, aggregation_strategy="simple")

nlp("I am going to buy 100 shares of cake tomorrow")
[{'entity_group': 'TICKER',
  'score': 0.9612462520599365,
  'word': ' cake',
  'start': 32,
  'end': 36}]

nlp("I am going to eat a cake tomorrow")
[]

📚 Documentation

Introduction

This is a model specifically designed to identify tickers in text. The model was trained on a transformed dataset from the following Kaggle dataset: https://www.kaggle.com/omermetinn/tweets-about-the-top-companies-from-2015-to-2020

🔧 Technical Details

The model's performance metrics are as follows:

precision: 0.914157
recall: 0.788824
f1: 0.846878

📄 License

No license information is provided in the original document, so this section is skipped.