fls-roberta

<!DOCTYPE html> <html> <body> <h1><b>FLS-RoBERTa</b></h1> <p><b>FLS-RoBERTa</b> is a pre-trained NLP model to classify forward-looking statements (FLS) in financial text, including:</p> <ul style="PADDING-LEFT: 40px"> <li>Financial Statements,</li> <li>Earnings Announcements,</li> <li>Earnings Call Transcripts,</li> <li>Corporate Social Responsibility (CSR) Reports,</li> <li>Environmental, Social, and Governance (ESG) News,</li> <li>Financial News,</li> <li>Etc.</li> </ul> <p>FLS-RoBERTa is built by further training and fine-tuning the RoBERTa Large language model using a large corpus of 10-K, 10-Q, 8-K, Earnings Call Transcripts, CSR Reports, ESG News, and Financial News text, labeled at the sentence level as forward-looking or non-forward-looking.</p> <p>The model gives softmax outputs for two labels: <b>FLS</b> (Forward-Looking Statement) and <b>Non-FLS</b> (Non-Forward-Looking Statement).</p> <p><b>How to classify text:</b></p> <p>The easiest way to use the model for single predictions is Hugging Face's text classification pipeline, which only needs a couple lines of code as shown in the following example:</p> <pre> <code> from transformers import pipeline fls_classifier = pipeline("text-classification", model="soleimanian/fls-roberta-large") print(fls_classifier("We expect revenue to grow by approximately 15% over the next fiscal year as we expand into new markets.")) </code> </pre> <p>I provide an example script via <a href="https://colab.research.google.com/drive/1WQqMH-FiC9MJlUYRA2aI7FWCUeoYuCs-?usp=sharing" target="_blank">Google Colab</a>. You can load your data to a Google Drive and run the script for free on a Colab. <p><b>Citation and contact:</b></p> <p>Please cite <a href="#" target="_blank">this paper</a> when you use the model. Feel free to reach out to [email protected] with any questions or feedback you may have.<p/> </body> </html>