HunFlair: An Easy-to-Use Tool for State-of-the-Art Biomedical Named Entity Recognition

TL;DR

HunFlair is a user-friendly biomedical NER tool integrated into Flair, offering high accuracy across multiple entity types with minimal setup, outperforming existing tools by an average of 7.26 percentage points.

Contribution

It introduces HunFlair, a highly accurate, easy-to-use biomedical NER tool integrated into the Flair framework, with significant performance improvements and simple installation.

Findings

Outperforms other NER tools by 7.26 percentage points on average.

Easy installation with a single command and minimal code.

Compatible across major operating systems.

Abstract

Summary: Named Entity Recognition (NER) is an important step in biomedical information extraction pipelines. Tools for NER should be easy to use, cover multiple entity types, highly accurate, and robust towards variations in text genre and style. To this end, we propose HunFlair, an NER tagger covering multiple entity types integrated into the widely used NLP framework Flair. HunFlair outperforms other state-of-the-art standalone NER tools with an average gain of 7.26 pp over the next best tool, can be installed with a single command and is applied with only four lines of code. Availability: HunFlair is freely available through the Flair framework under an MIT license: https://github.com/flairNLP/flair and is compatible with all major operating systems. Contact:{weberple,saengema,alan.akbik}@informatik.hu-berlin.de