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

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