Research map / Label-efficient and robust learning / Recognition and long-tail
Multi-View Consistency for Relation Extraction via Mutual Information and Structure Prediction
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 |
|---|---|---|---|
| induce structures with MVC instead of external-parser structure models (DRPC) | relation extraction · ACE 2005 test Avg. | F1: 63.92 -> 67.12 | Helped |
| MVC vs best structure-based model | relation extraction · SemEval 2010 | macro F1: 85.8 -> 86.1 | Helped |
| add ON-LSTM module (ablation) | MVC · ACE 2005 dev | F1: 67.5 -> 70.1 | Helped |
| add BiLSTM module (ablation) | MVC · ACE 2005 dev | F1: 68.0 -> 70.1 | Helped |
| add self-attention module (ablation) | MVC · ACE 2005 dev | F1: 68.4 -> 70.1 | Helped |
| add word contribution scores to KL structure loss (ablation) | MVC · ACE 2005 dev | F1: 69.2 -> 70.1 | Helped |
| add KL structure consistency (ablation) | MVC · ACE 2005 dev | F1: 68.1 -> 70.1 | Helped |
| add MI semantic consistency (ablation) | MVC · ACE 2005 dev | F1: 69.5 -> 70.1 | Helped |
| add control mechanism (ablation) | MVC · ACE 2005 dev | F1: 68.5 -> 70.1 | Helped |
| use MI for ON-LSTM and control for self-attention rather than MI for both (ablation) | MVC · ACE 2005 dev | F1: 67.3 -> 70.1 | Helped |
| use MI for ON-LSTM and control for self-attention rather than control for both (ablation) | MVC · ACE 2005 dev | F1: 68.9 -> 70.1 | Helped |
| add all three consistency constraints (KL, MI, control) (ablation) | MVC · ACE 2005 dev | F1: 67.1 -> 70.1 | Helped |
Closest papers by meaning
- DocKS-RAG: Optimizing Document-Level Relation Extraction through LLM-Enhanced Hybrid Prompt Tuning (ICML 2025 · similarity 0.88)
- A Hierarchical Network for Multimodal Document-Level Relation Extraction (AAAI 2024 · similarity 0.88)
- An Autoregressive Text-to-Graph Framework for Joint Entity and Relation Extraction (AAAI 2024 · similarity 0.86)
- Revisiting Document-Level Relation Extraction with Context-Guided Link Prediction (AAAI 2024 · similarity 0.86)
- Prototype-Guided Multimodal Relation Extraction based on Entity Attributes (AAAI 2025 · similarity 0.86)
- COMM: Concentrated Margin Maximization for Robust Document-Level Relation Extraction (AAAI 2025 · 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.