Cross-type biomedical named entity recognition with deep multi-task learning
Abstract
State-of-the-art biomedical named entity recognition (BioNER) systems often require handcrafted features specific to each entity type, such as genes, chemicals and diseases. Although recent studies explored using neural network models for BioNER to free experts from manual feature engineering, the performance remains limited by the available training data for each entity type.
Document Details
- Document Type
- Pub Defense Publication
- Publication Date
- Oct 11, 2018
- Source ID
- 10.1093/bioinformatics/bty869
Entities
People
- Curtis Langlotz
- Jiawei Han
- Jingbo Shang
- Marinka Žitnik
- Xiang Ren
- Xuan Wang
- Yu Zhang
- Yuhao Zhang
Organizations
- Defense Advanced Research Projects Agency
- Division of Information and Intelligent Systems
- National Institute of General Medical Sciences
- Stanford University
- United States Army Research Laboratory
- University of Illinois Urbana–Champaign
- University of Southern California