The Stanford CoreNLP NER uses an NER combiner that in principle supports running multiple NER models at the same time. However, currently our component only allows passing a single model, variant, mapping, etc. to the component. It would be good to have an approach to pass multiple.
The same could then maybe also be used for the OpenNLP NER.
The Stanford CoreNLP NER uses an NER combiner that in principle supports running multiple NER models at the same time. However, currently our component only allows passing a single model, variant, mapping, etc. to the component. It would be good to have an approach to pass multiple.
The same could then maybe also be used for the OpenNLP NER.
See also: https://github.com/dkpro/dkpro-core/issues/506