TY - JOUR T1 - Transfer learning for biomedical named entity recognition with neural networks JF - bioRxiv DO - 10.1101/262790 SP - 262790 AU - John M Giorgi AU - Gary D Bader Y1 - 2018/01/01 UR - http://biorxiv.org/content/early/2018/02/12/262790.abstract N2 - Motivation The explosive increase of biomedical literature has made information extraction an increasingly important tool for biomedical research. A fundamental task is the recognition of biomedical named entities (NER) such as genes/proteins, diseases, and species. Recently, a domain-independent method based on deep learning and statistical word embeddings, called long short-term memory network-conditional random field (LSTM-CRF), has been shown to outperform state-of-the-art entity-specific NER tools. However, this method is dependent on gold-standard corpora (GSCs) consisting of hand-labeled entities, which tend to be small but highly reliable. An alternative to GSCs are silver-standard corpora (SSCs), which are generated by harmonizing the annotations made by several automatic annotation systems. SSCs typically contain much more noise than GSCs but have the advantage of containing many more training examples. Ideally, these corpora could be combined to achieve the benefits of both, which is an opportunity for transfer learning. In this work, we analyze to what extent transfer learning improves upon state-of-the-art results for biomedical NER. We also attempt to identify the scenarios where transfer learning offers the biggest advantages.Results We demonstrate that transferring a deep neural network (DNN) trained on a large, noisy SSC to a smaller, but more reliable GSC improves upon state-of-the-art results for biomedical NER. Compared to a state-of-the-art baseline evaluated on 17 GSCs covering four different entity classes, transfer learning results in an average reduction in error of approximately 9%. We found transfer learning to be especially beneficial for target data sets with a small number of labels (approximately 5000 or less).Availability and implementation Source code for the LSTM-CRF is available at https://github.com/Franck-Dernoncourt/NeuroNER/ and links to the corpora are available at https://github.com/BaderLab/Transfer-Learning-BNER-Bioinformatics-2018/.Contact johnmg{at}cs.toronto.eduSupplementary information Supplementary data are available at Bioinformatics online. ER -