FinBERT: A Pretrained Language Model for Financial Communications

By Yi Yang, MA Uy, Allen Huang. arXiv.org, 2020

372 citations recorded by the source corpus.

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 this https URL. We hope this will be useful for practitioners and researchers working on financial NLP tasks.

Subfields: Artificial Intelligence, Management Science and Operations Research

View Paper: https://www.semanticscholar.org/paper/3578a7792904e6af3db8ffefdff86ab6a387c7c3

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

In Management Science and Operations Research

Citations in the corpus

AMMUS : A Survey of Transformer-based Pretrained Models in Natural Language Processing (2021, methodology): “Following the success of T-PTLMs in general English domain, T-PTLMs are also developed for other domains like Finance [31], Legal [32], [33], News”
FinQA: A Dataset of Numerical Reasoning over Financial Data (2021, background): “Recent works attempt to develop pre-trained models specialized for finance domain (Yang et al., 2020; Araci, 2019), and the downstream tasks are mostly sentiment classifications.”
Can Foundation Models Wrangle Your Data? (2022, neutral): “, earning reports, medical reports) [37, 103].”
HateBERT: Retraining BERT for Abusive Language Detection in English (2020, background): “…a growing interest in generating domain-speciﬁc BERT-like pre-trained language models, such as AlBERTo (Polignano et al., 2019), a Twitter-based BERT model in Italian, BioBERT for the biomedical domain in English (Lee et al., 2019), or FinBERT for the ﬁnancial domain in English (Yang et al., 2020).”
MWP-BERT: A Strong Baseline for Math Word Problems (2021, background): “It has been widely used in a large variety of NLP tasks and applications in other ﬁelds, like twitter text (Qudar and Mago, 2020), scientiﬁc text (Beltagy et al., 2019), biomedical data (Yoon et al., 2019; Lee et al., 2020), and ﬁnancial communications (Yang et al., 2020).”