README.md

---
license: cc-by-nc-sa-4.0

datasets:
- gtfintechlab/bank_of_korea

language:
- en

metrics:
- accuracy
- f1
- precision
- recall

base_model:
- bert-base-uncased

pipeline_tag: text-classification

library_name: transformers
---

# World of Central Banks Model

**Model Name:** Bank of Korea Uncertainty Estimation Model

**Model Type:** Text Classification

**Language:** English

**License:** [CC-BY-NC-SA 4.0](https://creativecommons.org/licenses/by-nc-sa/4.0/deed.en)

**Base Model:** [bert-base-uncased](https://huggingface.co/google-bert/bert-base-uncased)

**Dataset Used for Training:** [gtfintechlab/bank_of_korea](https://huggingface.co/datasets/gtfintechlab/bank_of_korea)

## Model Overview

Bank of Korea Uncertainty Estimation Model is a fine-tuned bert-base-uncased model designed to classify text data on **Uncertain Estimation**. This label is annotated in the bank_of_korea dataset, which focuses on meeting minutes for the Bank of Korea.

## Intended Use

This model is intended for researchers and practitioners working on subjective text classification for the Bank of Korea, particularly within financial and economic contexts. It is specifically designed to assess the **Uncertain Estimation** label, aiding in the analysis of subjective content in financial and economic communications.

## How to Use

To utilize this model, load it using the Hugging Face `transformers` library:

```python
from transformers import pipeline, AutoTokenizer, AutoModelForSequenceClassification, AutoConfig

# Load tokenizer, model, and configuration
tokenizer = AutoTokenizer.from_pretrained("gtfintechlab/bank_of_korea", do_lower_case=True, do_basic_tokenize=True)
model = AutoModelForSequenceClassification.from_pretrained("gtfintechlab/bank_of_korea", num_labels=2)
config = AutoConfig.from_pretrained("gtfintechlab/bank_of_korea")

# Initialize text classification pipeline
classifier = pipeline('text-classification', model=model, tokenizer=tokenizer, config=config, framework="pt")

# Classify Uncertain Estimation
sentences = [
    "[Sentence 1]",
    "[Sentence 2]"
]
results = classifier(sentences, batch_size=128, truncation="only_first")

print(results)
```

In this script:

- **Tokenizer and Model Loading:**  
  Loads the pre-trained tokenizer and model from `gtfintechlab/bank_of_korea`.

- **Configuration:**  
  Loads model configuration parameters, including the number of labels.

- **Pipeline Initialization:**  
  Initializes a text classification pipeline with the model, tokenizer, and configuration.

- **Classification:**  
  Labels sentences based on **Uncertain Estimation**.

Ensure your environment has the necessary dependencies installed.

## Label Interpretation

- **LABEL_0:** Certain; indicates that the sentence presents information definitively.
- **LABEL_1:** Uncertain; indicates that the sentence presents information with speculation, possibility, or doubt.

## Training Data

The model was trained on the bank_of_korea dataset, comprising annotated sentences from the Bank of Korea meeting minutes, labeled by **Uncertain Estimation**. The dataset includes training, validation, and test splits.

## Citation

If you use this model in your research, please cite the bank_of_korea:

```bibtex
@article{WCBShahSukhaniPardawala,
  title={Words That Unite The World: A Unified Framework for Deciphering Global Central Bank Communications},
  author={Agam Shah, Siddhant Sukhani, Huzaifa Pardawala et al.},
  year={2025}
}
```

For more details, refer to the [bank_of_korea dataset documentation](https://huggingface.co/gtfintechlab/bank_of_korea).

## Contact

For any bank_of_korea related issues and questions, please contact:

- Huzaifa Pardawala: huzaifahp7[at]gatech[dot]edu

- Siddhant Sukhani: ssukhani3[at]gatech[dot]edu

- Agam Shah: ashah482[at]gatech[dot]edu