FinBERT: A Pretrained Language Model for Financial Communications

TL;DR

FinBERT is a domain-specific pretrained language model for financial communications, demonstrating improved performance on financial sentiment classification tasks over generic BERT models.

Contribution

This work introduces FinBERT, a pretrained language model tailored for financial texts, filling a gap in domain-specific NLP tools for finance.

Findings

FinBERT outperforms generic BERT in financial sentiment classification.

Pretraining on financial corpora enhances model understanding of financial language.

Code and models are publicly available for research and practical use.

Abstract

Contextual pretrained language models, such as BERT (Devlin et al., 2019), have made significant breakthrough in various NLP tasks by training on large scale of unlabeled text re-sources.Financial sector also accumulates large amount of financial communication text.However, there is no pretrained finance specific language models available. In this work,we address the need by pretraining a financial domain specific BERT models, FinBERT, using a large scale of financial communication corpora. Experiments on three financial sentiment classification tasks confirm the advantage of FinBERT over generic domain BERT model. The code and pretrained models are available at https://github.com/yya518/FinBERT. We hope this will be useful for practitioners and researchers working on financial NLP tasks.