Hugging Face's logo

gtfintechlab
/
FOMC-RoBERTa

Text Classification
Transformers
PyTorch
English
roberta
finance
hawkish-dovish-classification
Inference Endpoints
Model card Files Community
2
FOMC-RoBERTa / README.md
shahagam4's picture
shahagam4
Update Dataset information
fe743f9
preview code
|
raw
history blame
2.71 kB
metadata
license: cc-by-nc-4.0
language:
  - en
tags:
  - finance
  - hawkish-dovish-classification
pipeline_tag: text-classification
widget:
  - text: >-
      Such a directive would imply that any tightening should be implemented
      promptly if developments were perceived as pointing to rising inflation.
  - text: >-
      The International Monetary Fund projects that global economic growth in
      2019 will be the slowest since the financial crisis.

Fine-Tuned model for FOMC hawkish-dovish-neutral classification task

This page contains the model for the ACL 2023 paper, "Trillion Dollar Words: A New Financial Dataset, Task & Market Analysis". This work was done at the Financial Services Innovation Lab of Georgia Tech. The FinTech lab is a hub for finance education, research and industry in the Southeast.

The paper is available at SSRN

Label Interpretation

LABEL_2: Neutral
LABEL_1: Hawkish
LABEL_0: Dovish

How to Use (Python Code) 

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

tokenizer = AutoTokenizer.from_pretrained("gtfintechlab/FOMC-RoBERTa", do_lower_case=True, do_basic_tokenize=True)
model = AutoModelForSequenceClassification.from_pretrained("gtfintechlab/FOMC-RoBERTa", num_labels=3)
config = AutoConfig.from_pretrained("gtfintechlab/FOMC-RoBERTa")

classifier = pipeline('text-classification', model=model, tokenizer=tokenizer, config=config, device=0, framework="pt")
results = classifier(["Such a directive would imply that any tightening should be implemented promptly if developments were perceived as pointing to rising inflation.", 
                      "The International Monetary Fund projects that global economic growth in 2019 will be the slowest since the financial crisis."], 
                      batch_size=128, truncation="only_first")

print(results)

Datasets

All the annotated datasets with train-test splits for 3 seeds are available on GitHub Page

Citation and Contact Information

Cite

Please cite our paper if you use any code, data, or models.

@article{shah2023trillion, 
  title={Trillion Dollar Words: A New Financial Dataset, Task & Market Analysis},
  author={Shah, Agam and Paturi, Suvan and Chava, Sudheer},
  journal={Available at SSRN 4447632},
  year={2023}
}

Contact Information

Please contact Agam Shah (ashah482[at]gatech[dot]edu) for any issues and questions.
GitHub: @shahagam4 Website: https://shahagam4.github.io/