%A Torge, Sunna %A Hahn, Waldemar %A Manjunath, Lalith %A Jäkel, René %D 2022 %T Named Entity Recognition for Specific Domains - Take Advantage of Transfer Learning %B 2022 %9 %! Named Entity Recognition for Specific Domains - Take Advantage of Transfer Learning %K %X Automated text analysis as named entity recognition (NER) heavily relies on large amounts of high-quality training data. For domain-specific NER transfer learning approaches aim to overcome the problem of lacking domain-specific training data. In this paper, we investigate transfer learning approaches in order to improve domain-specific NER in low-ressource domains. The first part of the paper is dedicated to information transfer from known to unknown entities using BiLSTM-CRF neural networks, considering also the influence of varying training data size. In the second part instead, pre-trained BERT models are fine-tuned to domain-specific German NER. The performance of models of both architectures is compared w.r.t. different hyperparameters and a set of 16 entities. The experiments are based on the revised German SmartData Corpus, and a baseline model, trained on this corpus. %U https://innove.org/ijist/index.php/ijist/article/view?path= %J International Journal of Information Science and Technology %0 Journal Article %R 10.57675/IMIST.PRSM/ijist-v6i3.189 %& 4 %P 12 %V 6 %N 3 %@ 2550-5114 %8 2022-09-16 %7 2022-09-16