Research map / Label-efficient and robust learning / Recognition and long-tail
Joint Entity and Relation Extraction with a Hybrid Transformer and Reinforcement Learning Based Model
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 |
|---|---|---|---|
| replace BiLSTM encoder with transformer (BERT) encoder (ablation) | JRE · TestSet1 relation | F-score: 0.560 -> 0.597 | Helped |
| add entity-wise position embedding (ablation) | JRE_T · TestSet1 relation | F-score: 0.597 -> 0.645 | Helped |
| add entity-wise position embedding (ablation) | JRE_T · TestSet1 entity | F-score: 0.668 -> 0.698 | Helped |
| add reinforcement learning noise-filtering agent (ablation) | JRE_T_PE · TestSet1 relation | F-score: 0.645 -> 0.686 | Helped |
| add reinforcement learning noise-filtering agent (ablation) | JRE_T_PE · TestSet2 relation | F-score: 0.598 -> 0.623 | Helped |
| add reinforcement learning noise-filtering agent (ablation) | JRE_T_PE · TestSet1 entity | F-score: 0.698 -> 0.725 | Helped |
| add RL agent (ablation) | JRE_T_PE · TestSet2 entity | F-score: 0.661 -> 0.708 | Helped |
| JRE_TRL versus HRL (word-level hierarchical RL) | JRE_TRL · joint entity-relation | F-score: 0.538 -> 0.542 | Helped |
| JRE_TRL versus HRL on entity precision | JRE_TRL · TestSet1 entity | precision: 0.737 -> 0.728 | Hurt |
Closest papers by meaning
- Large Scaled Relation Extraction With Reinforcement Learning (AAAI 2018 · similarity 0.91)
- A Hierarchical Framework for Relation Extraction with Reinforcement Learning (AAAI 2019 · similarity 0.89)
- SEE: Syntax-Aware Entity Embedding for Neural Relation Extraction (AAAI 2018 · similarity 0.88)
- A Unified Multi-Task Learning Framework for Joint Extraction of Entities and Relations (AAAI 2021 · similarity 0.88)
- An Autoregressive Text-to-Graph Framework for Joint Entity and Relation Extraction (AAAI 2024 · similarity 0.88)
- A Hierarchical Network for Multimodal Document-Level Relation Extraction (AAAI 2024 · similarity 0.86)
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.