Research map / Label-efficient and robust learning / Noisy labels
Distant IE by Bootstrapping Using Lists and Document Structure
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 list, section, and neighbor coupling with label propagation to train the classifier | DIEBOLDS · Labeled pages, Disease | F1: 0.175 -> 0.209 | Helped |
| Use list, section, and neighbor coupling with label propagation to train the classifier | DIEBOLDS · Labeled pages, Drug | F1: 0.037 -> 0.090 | Helped |
| Use DIEBOLDS rather than Freebase facts as the answer source | BioASQ questions · BioASQ questions | Recall: 0.109 -> 0.195 | Helped |
| Add section and neighbor edges to list-based label propagation (ablation) | DIEBOLDS-SN · Labeled pages, Disease | F1: 0.191 -> 0.209 | Helped |
| Add section and neighbor edges to list-based label propagation (ablation) | DIEBOLDS-SN · Labeled pages, Drug | F1: 0.082 -> 0.090 | Helped |
| Add section edges (ablation) | DIEBOLDS-S · Labeled pages, Disease | F1: 0.198 -> 0.209 | Helped |
| Add section edges (ablation) | DIEBOLDS-S · Labeled pages, Drug | F1: 0.088 -> 0.090 | Helped |
| Add neighbor edges (ablation) | DIEBOLDS-N · Labeled pages, Disease | F1: 0.194 -> 0.209 | Helped |
| Add neighbor edges (ablation) | DIEBOLDS-N · Labeled pages, Drug | F1: 0.085 -> 0.090 | Helped |
| Add list structure to distant supervision | DS1 · Labeled pages, Disease | F1: 0.175 -> 0.184 | Helped |
| Add list structure to distant supervision | DS1 · Labeled pages, Drug | F1: 0.037 -> 0.057 | Helped |
| Add distantly labeled examples from a structured corpus without coupling propagation | DS1 · Labeled pages, Disease | F1: 0.175 -> 0.174 | No clear effect |
Closest papers by meaning
- Bootstrapping Distantly Supervised IE Using Joint Learning and Small Well-Structured Corpora (AAAI 2017 · similarity 0.90)
- SAIL: Sample-Centric In-Context Learning for Document Information Extraction (AAAI 2025 · similarity 0.83)
- Small Language Model Makes an Effective Long Text Extractor (AAAI 2025 · similarity 0.82)
- A Positive-Unlabeled Metric Learning Framework for Document-Level Relation Extraction with Incomplete Labeling (AAAI 2024 · similarity 0.82)
- An Autoregressive Text-to-Graph Framework for Joint Entity and Relation Extraction (AAAI 2024 · similarity 0.82)
- Span Graph Transformer for Document-Level Named Entity Recognition (AAAI 2024 · similarity 0.82)
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.