In developing the NER model, naming annotations are used as an important part of the training process. The impact of using different naming annotations on NER performance has been a concern in the research community. So,the writer wants to once again, test the impact of using different naming annotations using the spaCy library on English documents. Using 2 naming schemes namely BIO and IOBES, using the spaCy model to get 0.96 accuracy for BIO and 0.95 for IOBES.
Obs.: This plugin requires at least one statistics/report plugin to be enabled. If your statistics plugins provide more than one metric then please also select a main metric on the admin's site settings page and/or on the journal manager's settings pages.