Biomedical named entity recognition (NER) using second-order the conditional random fields model

2011 | The 3rd International Conference on Computer Technology and Development.
Share via twitter Share via email Download PDF

Supattanawaree Thipchareon
Jeerayut Chaijaruwanich


—Biomedical named entity recognition (NER) is an important technique for biological information extraction. Here, we have proposed a model using machine learning where biological terms are recognized using second-order conditional random fields (CRFs). From our experiments with the JNLPBA 2004 dataset, the CRFs labeling model returns an F-score prediction value of almost 99%.