Finbert Tone

🚀 FinBERT

FinBERT is a pre - trained BERT model on financial communication text, aiming to boost financial NLP research and practice.

✨ Features

• Pre - trained on Financial Corpus: FinBERT is pre - trained on three financial communication corpora with a total of 4.9B tokens, including 2.5B tokens from Corporate Reports 10 - K & 10 - Q, 1.3B tokens from Earnings Call Transcripts, and 1.1B tokens from Analyst Reports.
• Fine - tuned for Tone Analysis: The released finbert - tone model is a fine - tuned version of FinBERT on 10,000 manually annotated sentences from analyst reports, achieving superior performance in financial tone analysis.

📦 Installation

No specific installation steps are provided in the original document.

💻 Usage Examples

Basic Usage

from transformers import BertTokenizer, BertForSequenceClassification
from transformers import pipeline

finbert = BertForSequenceClassification.from_pretrained('yiyanghkust/finbert-tone',num_labels=3)
tokenizer = BertTokenizer.from_pretrained('yiyanghkust/finbert-tone')

nlp = pipeline("sentiment-analysis", model=finbert, tokenizer=tokenizer)

sentences = ["there is a shortage of capital, and we need extra financing",  
             "growth is strong and we have plenty of liquidity", 
             "there are doubts about our finances", 
             "profits are flat"]
results = nlp(sentences)
print(results)  #LABEL_0: neutral; LABEL_1: positive; LABEL_2: negative

📚 Documentation

Technical Details

FinBERT is a BERT model pre - trained on financial communication text. It is trained on three financial communication corpora. More technical details on FinBERT can be found Click Link.

Citation

If you use the model in your academic work, please cite the following paper:

Huang, Allen H., Hui Wang, and Yi Yang. "FinBERT: A Large Language Model for Extracting Information from Financial Text." Contemporary Accounting Research (2022).

📄 License

No license information is provided in the original document.