Research map / Label-efficient and robust learning / Recognition and long-tail
Improving Neural Relation Extraction with Positive and Unlabeled Learning
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 |
|---|---|---|---|
| Use PU learning with RL sentence selection and positive, unlabeled, and combined bag representations | CNN/PCNN relation extraction · Held-out evaluation | Precision-recall performance | Helped |
| Add relation embeddings to the RL selector state (ablation) | RL sentence selector · Held-out evaluation | Precision-recall performance | Helped |
| Use RL selection of positive sentences instead of averaging all bag sentences | CNN/PCNN relation extraction · Held-out evaluation | Precision-recall performance | Helped |
| Use piecewise max-pooling rather than CNN sentence encoding | PU relation extraction · Held-out evaluation | Precision-recall performance | Helped |
| Add the PU-combined representation and its loss (ablation) | PU relation extractor · Held-out evaluation | Precision-recall performance | Helped |
| Add the UNL-based representation and its loss (ablation) | PU relation extractor · Held-out evaluation | Precision-recall performance | Helped |
| Include selected positive and unlabeled instances in bag-level training rather than using positives alone | PU relation extractor · Held-out evaluation | Precision-recall performance | Helped |
Closest papers by meaning
- Large Scaled Relation Extraction With Reinforcement Learning (AAAI 2018 · similarity 0.89)
- Reinforcement Learning for Relation Classification From Noisy Data (AAAI 2018 · similarity 0.89)
- Competition or Cooperation? Exploring Unlabeled Data via Challenging Minimax Game for Semi-supervised Relation Extraction (AAAI 2023 · similarity 0.87)
- A Positive-Unlabeled Metric Learning Framework for Document-Level Relation Extraction with Incomplete Labeling (AAAI 2024 · similarity 0.87)
- Enhancing Relation Extraction via Supervised Rationale Verification and Feedback (AAAI 2025 · similarity 0.85)
- Enhancing Low-Resource Relation Representations through Multi-View Decoupling (AAAI 2024 · 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.