Research map / Label-efficient and robust learning / Recognition and long-tail
A Neural Multi-Task Learning Framework to Jointly Model Medical Named Entity Recognition and Normalization
Sendong Zhao, Ting Liu, Sicheng Zhao, Fei Wang
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| add shared multi-task learning with MER-to-MEN and MEN-to-MER feedback (ablation) | Bi-LSTM-CNNs-CRF for medical entity recognition and normalization · NCBI Disease | MER F1: 0.8248 -> 0.8743 | Improved |
| add shared multi-task learning with MER-to-MEN and MEN-to-MER feedback (ablation) | Bi-LSTM-CNNs-CRF for medical entity recognition and normalization · NCBI Disease | MEN F1: 0.8061 -> 0.8823 | Improved |
| add shared multi-task learning with MER-to-MEN and MEN-to-MER feedback (ablation) | Bi-LSTM-CNNs-CRF for medical entity recognition and normalization · BC5CDR | MER F1: 0.8466 -> 0.8763 | Improved |
| add shared multi-task learning with MER-to-MEN and MEN-to-MER feedback (ablation) | Bi-LSTM-CNNs-CRF for medical entity recognition and normalization · BC5CDR | MEN F1: 0.8449 -> 0.8917 | Improved |
| add MER-to-MEN feedback (ablation) | MTL + Bi-LSTM-CNNs · NCBI Disease | MER F1: 0.8647 -> 0.8723 | Improved |
| add MER-to-MEN feedback (ablation) | MTL + Bi-LSTM-CNNs · NCBI Disease | MEN F1: 0.8693 -> 0.8731 | Improved |
| add MEN-to-MER feedback (ablation) | MTL + Bi-LSTM-CNNs · NCBI Disease | MER F1: 0.8647 -> 0.8653 | Improved |
| add MEN-to-MER feedback (ablation) | MTL + Bi-LSTM-CNNs · NCBI Disease | MEN F1: 0.8693 -> 0.8706 | Improved |
| add both feedback directions rather than MER-to-MEN feedback alone (ablation) | MTL + Bi-LSTM-CNNs · NCBI Disease | MEN F1: 0.8731 -> 0.8823 | Improved |
| add character-level CNN representations (ablation) | single-task Bi-LSTM · NCBI Disease | MER F1: 0.8075 -> 0.8246 | Improved |
| add a CRF layer (ablation) | Bi-LSTM-CNNs · NCBI Disease | MER F1: 0.8246 -> 0.8248 | No clear effect |
| remove dropout (ablation) | MTL-MEN&MER_feedback + Bi-LSTM-CNNs · NCBI Disease | MER F1: 0.8743 -> 0.8669 | Hurt |
Closest papers by meaning
- Multi-Task Medical Concept Normalization Using Multi-View Convolutional Neural Network (AAAI 2018 · similarity 0.90)
- Uni-Med: A Unified Medical Generalist Foundation Model For Multi-Task Learning Via Connector-MoE (NeurIPS 2024 · similarity 0.84)
- Joint-Task Regularization for Partially Labeled Multi-Task Learning (CVPR 2024 · similarity 0.82)
- Automated Multi-Task Learning for Joint Disease Prediction on Electronic Health Records (NeurIPS 2024 · similarity 0.82)
- An Information-theoretic Multi-task Representation Learning Framework for Natural Language Understanding (AAAI 2025 · similarity 0.81)
- Distribution Matching for Multi-Task Learning of Classification Tasks: A Large-Scale Study on Faces & Beyond (AAAI 2024 · similarity 0.81)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.
