Marinka Zitnik

Fusing bits and DNA

  • Increase font size
  • Default font size
  • Decrease font size
Home

Biomedical Entity Recognition with Deep Multi-Task Learning

We propose a deep multi-task learning approach for biomedical named entity recognition, which is a fundamental task in the mining of biomedical text data. The new approach saves human efforts and frees biomedical experts from the need to painstakingly generate entity features by hand. Furthermore, it achieves excellent performance using only a limited amount of training data.

The approach can help scientists to better exploit knowledge buried in vast biomedical literature. I have enjoyed working on this project with researchers from Stanford, USC, and UIUC.