FinBERT-MRC: financial named entity recognition using BERT under the machine reading comprehension paradigm

TL;DR

This paper introduces FinBERT-MRC, a novel approach that formulates financial named entity recognition as a machine reading comprehension task, leveraging BERT and query design to improve extraction accuracy from financial texts.

Contribution

The paper proposes a new MRC-based model for FinNER that outperforms traditional sequence tagging models by utilizing query-based information extraction with BERT.

Findings

Achieves high F1 scores of 92.78% and 96.80% on two datasets.

Outperforms sequence tagging models like BiLSTM-CRF and BERT-Tagger.

Demonstrates the effectiveness of MRC formulation in financial NER tasks.

Abstract

Financial named entity recognition (FinNER) from literature is a challenging task in the field of financial text information extraction, which aims to extract a large amount of financial knowledge from unstructured texts. It is widely accepted to use sequence tagging frameworks to implement FinNER tasks. However, such sequence tagging models cannot fully take advantage of the semantic information in the texts. Instead, we formulate the FinNER task as a machine reading comprehension (MRC) problem and propose a new model termed FinBERT-MRC. This formulation introduces significant prior information by utilizing well-designed queries, and extracts start index and end index of target entities without decoding modules such as conditional random fields (CRF). We conduct experiments on a publicly available Chinese financial dataset ChFinAnn and a real-word bussiness dataset AdminPunish. FinBERT-MRC model achieves average F1 scores of 92.78% and 96.80% on the two datasets, respectively, with average F1 gains +3.94% and +0.89% over some sequence tagging models including BiLSTM-CRF, BERT-Tagger, and BERT-CRF. The source code is available at https://github.com/zyz0000/FinBERT-MRC.