Research map / Label-efficient and robust learning / Recognition and long-tail
Progressive Multi-task Learning with Controlled Information Flow for Joint Entity and Relation Extraction
Read the paperCheck your idea against 108,967 papers
AI-extracted summary. Written by AI from the paper's title only (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 progressive task-specific representations using controlled early predictions and explicit task interactions | joint entity and relation extraction · NYT exact match | F1: 76.9 -> 84.2 | Helped |
| add progressive task-specific representations using controlled early predictions and explicit task interactions | joint entity and relation extraction · WebNLG exact match | F1: 75.7 -> 78.2 | Helped |
| add BERT initialization to PMEI | PMEI · NYT partial match | F1: 87.8 -> 90.1 | Helped |
| add BERT initialization to PMEI | PMEI · WebNLG partial match | F1: 88.1 -> 92.0 | Helped |
| add BERT initialization to PMEI | PMEI · NYT10 partial match | F1: 72.6 -> 74.5 | Helped |
| add BERT initialization to PMEI | PMEI · NYT11 partial match | F1: 57.2 -> 57.7 | Helped |
| add explicit interactions between task predictions (ablation) | PMEI · NYT exact match | F1: 78.7 -> 84.2 | Helped |
| add explicit interactions between task predictions (ablation) | PMEI · WebNLG exact match | F1: 77.7 -> 78.2 | Helped |
| add stochastic maps to control information flow (ablation) | PMEI · NYT exact match | F1: 82.7 -> 84.2 | Helped |
| add stochastic maps to control information flow (ablation) | PMEI · WebNLG exact match | F1: 76.9 -> 78.2 | Helped |
| add GRUCells instead of MLPs for the encoder distributions (ablation) | PMEI · NYT exact match | F1: 83.4 -> 84.2 | Helped |
| add GRUCells instead of MLPs for the encoder distributions (ablation) | PMEI · WebNLG exact match | F1: 77.5 -> 78.2 | Helped |
Closest papers by meaning
- Provable Multi-Task Representation Learning by Two-Layer ReLU Neural Networks (ICML 2024 · similarity 0.87)
- Continual Relation Extraction via Sequential Multi-Task Learning (AAAI 2024 · similarity 0.86)
- Distribution Matching for Multi-Task Learning of Classification Tasks: A Large-Scale Study on Faces & Beyond (AAAI 2024 · similarity 0.85)
- An Information-theoretic Multi-task Representation Learning Framework for Natural Language Understanding (AAAI 2025 · similarity 0.85)
- Learning Task-Agnostic Representations through Multi-Teacher Distillation (NeurIPS 2025 · similarity 0.84)
- Identifying and Mitigating Spurious Correlation in Multi-Task Learning (CVPR 2025 · similarity 0.84)
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.