Transformer based named entity recognition for place name extraction from unstructured text

Place names embedded in online natural language text present a useful source of geographic information. Despite this, many methods for the extraction place from use pre-trained models that were not explicitly designed this task. Our paper builds five custom-built Named Entity Recognition (NER) and evaluates them against three popular pre-built name extraction. The are evaluated using set manually annotated Wikipedia articles with reference to F1 score metric. best performing model achieves an 0.939 compared 0.730 model. is then used extract all Great Britain, demonstrating ability more accurately capture unknown volunteered sources