Biomedical Named Entity Recognition at Scale

TL;DR

This paper introduces a scalable, high-performance biomedical NER model built on Spark that achieves state-of-the-art results without relying on heavy contextual embeddings, and is openly available for broad use.

Contribution

The authors reimplement a deep learning NER architecture on Spark, achieving new benchmarks in biomedical NER without using BERT, and provide an open-source, scalable, multi-language compatible tool.

Findings

Achieved new state-of-the-art results on seven biomedical benchmarks.

Improved BC4CHEMD to 93.72%, Species800 to 80.91%, JNLPBA to 81.29%.

Model is scalable, GPU-supported, and available in multiple programming languages.

Abstract

Named entity recognition (NER) is a widely applicable natural language processing task and building block of question answering, topic modeling, information retrieval, etc. In the medical domain, NER plays a crucial role by extracting meaningful chunks from clinical notes and reports, which are then fed to downstream tasks like assertion status detection, entity resolution, relation extraction, and de-identification. Reimplementing a Bi-LSTM-CNN-Char deep learning architecture on top of Apache Spark, we present a single trainable NER model that obtains new state-of-the-art results on seven public biomedical benchmarks without using heavy contextual embeddings like BERT. This includes improving BC4CHEMD to 93.72% (4.1% gain), Species800 to 80.91% (4.6% gain), and JNLPBA to 81.29% (5.2% gain). In addition, this model is freely available within a production-grade code base as part of the open-source Spark NLP library; can scale up for training and inference in any Spark cluster; has GPU support and libraries for popular programming languages such as Python, R, Scala and Java; and can be extended to support other human languages with no code changes.