Extracting IT Knowledge Using Named Entity Recognition Based on BERT from IOB Annotated Job Descriptions

Named Entity Recognition (NER) is a technique from the field of Natural Language Processing (NLP) that strives to identify entities such as names of people, organizations, and places in a given text. In this study, we investigate the use of NER to extract knowledge from unstructured data comprising descriptions of computer workstations. To this end, we use annotated data in IOB (Inside, Outside, Beginning) format. Our approach includes presenting the implemented design, preparing the dataset, training the BERT model, and presenting the performance results of our NER model through rigorous evaluation. Measures such as precision, recall, and F1-Score are used to assess the model's accuracy in entity recognition.