TY  - CPAPER
U1  - Konferenzveröffentlichung
A1  - Schwarz, Pia
ED  - Luz de Araujo, Pedro Henrique
ED  - Baumann, Andreas
ED  - Gromann, Dagmar
ED  - Krenn, Brigitte
ED  - Roth, Benjamin
ED  - Wiegand, Michael
T1  - Semiautomatic data generation for academic Named Entity Recognition in German text corpora
T2  - Proceedings of the 20th Conference on Natural Language Processing (KONVENS 2024). September 10-13, 2024
N2  - 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%.
KW  - Named Entity Recognition
KW  - Deutsch
KW  - Korpus <Linguistik>
KW  - Großes Sprachmodell
KW  - Computerlinguistik
KW  - data generation
KW  - text corpora
KW  - academic Named Entity Recognition
KW  - named entity
KW  - BERT model
Y1  - 2024
U6  - https://nbn-resolving.org/urn:nbn:de:bsz:mh39-128423
UN  - https://nbn-resolving.org/urn:nbn:de:bsz:mh39-128423
UR  - https://aclanthology.org/2024.konvens-main.20
SP  - 173
EP  - 181
PB  - Association for Computational Linguistics
CY  - Wien
ER  -