@inproceedings{Schwarz2024,
  author    = {Schwarz, Pia},
  title     = {Semiautomatic data generation for academic Named Entity Recognition in German text corpora},
  booktitle = {Proceedings of the 20th Conference on Natural Language Processing (KONVENS 2024). September 10-13, 2024},
  editor    = {Luz de Araujo, Pedro Henrique and Baumann, Andreas and Gromann, Dagmar and Krenn, Brigitte and Roth, Benjamin and Wiegand, Michael},
  url       = {https://aclanthology.org/2024.konvens-main.20},
  pages     = {173 -- 181},
  year      = {2024},
  abstract  = {An NER model is trained to recognize three types of entities in academic contexts: person, organization, and research area. Training data is generated semiautomatically from newspaper articles with the help of word lists for the individual entity types, an off-the-shelf NE recognizer, and an LLM. Experiments fine-tuning a BERT model with different strategies of post-processing the automatically generated data result in several NER models achieving overall F1 scores of up to 92.45\%.},
  subject      = {Named Entity Recognition},
  language  = {en}
}