PUB - Publikationen an der Universität Bielefeld

This work presents the development of a multi-task workflow for named entity recognition (NER) and following relation extraction (RE) from biomedical literature using neural networks. With the increasing amount of data, the automated information extraction becomes more and more important in order to gain relevant information and draw scientific conclusions. The application of neural networks for text mining has been shown to achieve promising results. One of the biggest problems of training neural networks is the limited availability of labeled data. This is especially true for the biomedical field because of its complexity. Therefore, this work focuses on two methods. The first is to make use of contextual word models using unsupervised pre-training (with large amounts of data). On top of this, specific models for NER and RE are trained using annotated data. This is done using a multi-task which means that the model is trained on different, but related data sets simultaneously. On the application side, the aim is to generate a model able to predict microRNA-disease associations. The keyword “miRNA” yields nowadays more than 80,000 publication entries in PubMed. Since they are promising drug targets, the automatic extraction of miRNA-disease associations is of enormous interest.For the development of the workflow, state-of-the-art methods are adapted, combined and evaluated on the use-case mentioned.