BioFLAIR: Pretrained Pooled Contextualized Embeddings for Biomedical Sequence Labeling Tasks

13 Aug 2019Shreyas SharmaRon Daniel Jr

Biomedical Named Entity Recognition (NER) is a challenging problem in biomedical information processing due to the widespread ambiguity of out of context terms and extensive lexical variations. Performance on bioNER benchmarks continues to improve due to advances like BERT, GPT, and XLNet... (read more)

PDF Abstract

Evaluation results from the paper


 SOTA for Named Entity Recognition on BC5CDR (using extra training data)

     Get a GitHub badge
Task Dataset Model Metric name Metric value Global rank Uses extra
training data
Compare
Named Entity Recognition BC5CDR BioFLAIR F1 89.42 # 1
Named Entity Recognition JNLPBA BioFLAIR F1 77.03 # 2
Named Entity Recognition LINNAEUS BioFLAIR F1 87.02 # 1
Named Entity Recognition NCBI-disease BioFLAIR F1 88.85 # 1
Named Entity Recognition Species-800 BioFLAIR F1 82.44 # 1