Position-aware deep multi-task learning for drug–drug interaction extraction

Keyphrases

• Drug Interactions 100%
• Deep multi-task Learning 100%
• Interaction Extraction 100%
• Position-aware 100%
• Position Attention 100%
• Interaction Type 66%
• Biomedical Text 66%
• Bidirectional Long Short-term Memory (BiLSTM) 66%
• Hidden States 33%
• Healthcare Professionals 33%
• Attention Task 33%
• Learning Approaches 33%
• Word Position 33%
• State-of-the-art Techniques 33%
• Adverse Drug Events 33%
• Interaction Classification 33%
• Targeted Drugs 33%
• Word Embedding 33%
• Type Identification 33%
• Attention Weight 33%
• Relative Position Information 33%
• Multi-task Learning Framework 33%
• Position Embedding 33%
• DrugBank 33%
• Multi-task Learning 33%
• Attention-based 33%

Computer Science

• Multitask Learning 100%
• Bidirectional Long Short-Term Memory Network 50%
• Learning Framework 25%
• Healthcare Professional 25%
• Learning Approach 25%
• Position Information 25%
• Relative Position 25%
• Embedding Position 25%
• Word Embedding 25%