Our own BIO NER trained on the BioCreative 2 dataset, using the Stanford CRF User: mihais Date: 2/27/15
Combines RuleNER and CRFNER into a, surprise surprise, hybrid NER User: mihais Date: 2/9/17
User: mihais Date: 10/20/16
Validates if the span identified as an entity is actually valid User: mihais Date: 10/24/16
Rule-based NER for the Bio domain If useLemmas is true, tokens are matched using lemmas, otherwise using words knownCaseInsensitives contains single-token entities that can be spelled using lower case, according to the KB(s) The order of the matchers is important: it indicates priority during ties (first has higher priority) User: mihais Date: 5/11/15
Computes P, R, F1 scores for the complete mentions produced by a sequence tagger User: mihais Date: 2/27/15
User: mihais Date: 2/7/16 Last Modified: Update for 5-column NER override file format.
Loads the KBs from bioresources under org/clulab/reach/kb/ner These must be generated offline by KBGenerator; see bioresources/ner_kb.sh User: mihais.
Loads the KBs from bioresources under org/clulab/reach/kb/ner These must be generated offline by KBGenerator; see bioresources/ner_kb.sh User: mihais. 2/7/16. Last Modified: Update to use external configuration file.