FOMC RoBERTa

🚀 聯邦公開市場委員會鷹派 - 鴿派 - 中立分類任務微調模型

本頁面包含ACL 2023論文 "萬億美元詞彙：全新金融數據集、任務與市場分析" 所使用的模型。這項工作由佐治亞理工學院金融服務創新實驗室完成。該金融科技實驗室是美國東南部金融教育、研究和行業的中心。

論文可在 SSRN 上獲取。

🚀 快速開始

✨ 主要特性

本模型用於聯邦公開市場委員會（FOMC）聲明的鷹派 - 鴿派 - 中立分類任務，能夠有效幫助金融從業者和研究者分析貨幣政策立場。

📦 安裝指南

本項目使用Python代碼進行模型調用，需要安裝transformers庫。

💻 使用示例

基礎用法

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)

📚 詳細文檔

標籤解釋

數據集

所有帶訓練 - 測試劃分的標註數據集（3個隨機種子）可在 GitHub頁面 上獲取。

📄 許可證

本項目採用 CC BY - NC 4.0 許可證。

🔗 引用與聯繫信息

引用

如果您使用了本項目的代碼、數據或模型，請引用我們的論文：

@inproceedings{shah-etal-2023-trillion,
    title = "Trillion Dollar Words: A New Financial Dataset, Task {\&} Market Analysis",
    author = "Shah, Agam  and
      Paturi, Suvan  and
      Chava, Sudheer",
    booktitle = "Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)",
    month = jul,
    year = "2023",
    address = "Toronto, Canada",
    publisher = "Association for Computational Linguistics",
    url = "https://aclanthology.org/2023.acl-long.368",
    doi = "10.18653/v1/2023.acl-long.368",
    pages = "6664--6679",
    abstract = "Monetary policy pronouncements by Federal Open Market Committee (FOMC) are a major driver of financial market returns. We construct the largest tokenized and annotated dataset of FOMC speeches, meeting minutes, and press conference transcripts in order to understand how monetary policy influences financial markets. In this study, we develop a novel task of hawkish-dovish classification and benchmark various pre-trained language models on the proposed dataset. Using the best-performing model (RoBERTa-large), we construct a measure of monetary policy stance for the FOMC document release days. To evaluate the constructed measure, we study its impact on the treasury market, stock market, and macroeconomic indicators. Our dataset, models, and code are publicly available on Huggingface and GitHub under CC BY-NC 4.0 license.",
}

聯繫信息

如有任何問題，請聯繫 Agam Shah（ashah482[at]gatech[dot]edu）。
GitHub: @shahagam4 個人網站: https://shahagam4.github.io/