BioNerFlair: biomedical named entity recognition using flair embedding and sequence tagger
This work addresses the problem of efficiently extracting biomedical entities from research articles for scientists and researchers, offering an incremental improvement over existing methods.
The paper tackles biomedical named entity recognition by introducing BioNerFlair, which uses Flair and GloVe embeddings with a Bidirectional LSTM-CRF sequence tagger, achieving state-of-the-art F1-scores on multiple benchmarks, such as 90.17 on BC2GM and 94.03 on BC4CHEMD.
Motivation: The proliferation of Biomedical research articles has made the task of information retrieval more important than ever. Scientists and Researchers are having difficulty in finding articles that contain information relevant to them. Proper extraction of biomedical entities like Disease, Drug/chem, Species, Gene/protein, can considerably improve the filtering of articles resulting in better extraction of relevant information. Performance on BioNer benchmarks has progressively improved because of progression in transformers-based models like BERT, XLNet, OpenAI, GPT2, etc. These models give excellent results; however, they are computationally expensive and we can achieve better scores for domain-specific tasks using other contextual string-based models and LSTM-CRF based sequence tagger. Results: We introduce BioNerFlair, a method to train models for biomedical named entity recognition using Flair plus GloVe embeddings and Bidirectional LSTM-CRF based sequence tagger. With almost the same generic architecture widely used for named entity recognition, BioNerFlair outperforms previous state-of-the-art models. I performed experiments on 8 benchmarks datasets for biomedical named entity recognition. Compared to current state-of-the-art models, BioNerFlair achieves the best F1-score of 90.17 beyond 84.72 on the BioCreative II gene mention (BC2GM) corpus, best F1-score of 94.03 beyond 92.36 on the BioCreative IV chemical and drug (BC4CHEMD) corpus, best F1-score of 88.73 beyond 78.58 on the JNLPBA corpus, best F1-score of 91.1 beyond 89.71 on the NCBI disease corpus, best F1-score of 85.48 beyond 78.98 on the Species-800 corpus, while near best results was observed on BC5CDR-chem, BC3CDR-disease, and LINNAEUS corpus.