Does anyone have experience with fine-tuning an NER model on out-of-domain data? Did the fine-tuning succeed, and approximately how much data was needed?
To clarify, e.g., starting with a NER model to identify persons and locations, and fine-tuning the model to find, for example:
Electric Vehicles (EVs)(e.g., Tesla Model 3, Polestar 2),Charging Stations– (e.g., Ionity, Tesla Supercharger), andInfrastructure Projects– (e.g., Northvolt Battery Factory).
