#170 · Primary category： NLP Tools & Text Processing
FinBERT
A Pretrained BERT Model for Financial Communications. https://arxiv.org/abs/2006.08097
Project last updated：07/23/23
GitHub Stars
659
Forks
145
Contributors
4
License
Apache-2.0
Why we included this project
For teams working with earnings call transcripts, analyst reports, or SEC filings, FinBERT was trained on roughly 4.9 billion tokens of that kind of text. That training data is why it handles the vocabulary and phrasing of disclosures better than a general-purpose language model. The repo includes fine-tuned checkpoints for sentiment, ESG, and forward-looking statement classification, all hosted on Hugging Face and loadable in a few lines with the transformers library. Two notebooks show how to apply the ready-made models and how to fine-tune your own, so a team can get going on financial text analysis without training a model from scratch.
Articles for this project
No articles for this project yet.
To suggest a topic or contribute an article, contact us.
Related projects in this category
flair
A very simple framework for state-of-the-art Natural Language Processing (NLP)
compromise
modest natural-language processing
tokenizers
💥 Fast State-of-the-Art Tokenizers optimized for Research and Production
CoreNLP
CoreNLP: A Java suite of core NLP tools for tokenization, sentence segmentation, NER, parsing, coreference, sentiment analysis, etc.
Chinese-Word-Vectors
100+ Chinese Word Vectors 上百种预训练中文词向量