Biomedical Named Entity Recognition Based on Skip-Chain CRFS
Zhihua Liao, Hongguang Wu · 2012
Biomedical named entity recognition (BioNER) is one subtask of named entity recognition (NER) research. Although there are a number of named entity recognition systems, they can not obtain good performances extended to biomedical subfield. BioNER becomes a challenging work. We employ a skip-chain conditional random fields (CRFs) model for BioNER. This model completely considers to the long-range dependencies about biomedical information. These distant dependencies are powerful to identify some frequent appearing named entities and to classify them, especially for both classes protein and cell type. When we test the GENIA corpus, our approach obtains significant improvement over other methods, which achieves precision, recall and F-score of 72.8%, 73.6% and 73.2%, respectively.