Research map / Label-efficient and robust learning / Semi-supervised learning
Bootstrapping Distantly Supervised IE Using Joint Learning and Small Well-Structured Corpora
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 |
|---|---|---|---|
| Combine section-filtered structured-corpus seeds with target-corpus examples and concept mentions | DIEJOB vs. distant-supervision and latent-variable baselines · Labeled pages, disease domain | F1: 0.300 -> 0.324 | Helped |
| Use joint label propagation with structured and target corpus information | DIEJOB vs. strongest reported latent-variable baseline · Labeled pages, drug domain | F1: 0.163 -> 0.306 | Helped |
| Add structured-corpus examples to target-corpus training examples | DIEJOB_Both vs. DIEJOB_Target · Labeled pages, disease domain | F1: 0.275 -> 0.324 | Helped |
| Add structured-corpus examples to target-corpus training examples | DIEJOB_Both vs. DIEJOB_Target · Labeled pages, drug domain | F1: 0.300 -> 0.306 | No clear effect |
| Use structured-corpus examples in addition to target-corpus examples (ablation) | DIEJOB graph variants · Disease domain tuning dataset | F1 | Helped |
| Mix structured-corpus and target-corpus examples (ablation) | DIEJOB graph variants · Drug domain tuning dataset | F1 | Hurt |
| Use only target-corpus examples among the top N propagated examples (ablation) | DIEJOB_Target vs. DIEJOB_Both · Drug domain tuning dataset | F1 | Helped |
| Use the R_sR_t graph variant (ablation) | DIEJOB_Target · Drug domain tuning dataset | F1 | Helped |
| Use the R_sC_s graph variant (ablation) | DIEJOB_Both · Disease domain tuning dataset | F1 | Helped |
| Use the R_sC_sR_t graph variant (ablation) | DIEJOB_Both · Disease domain tuning dataset | F1 | Helped |
| Use relation mentions, concept mentions, or both as graph nodes alongside seed relation mentions (ablation) | DIEJOB label-propagation graph · Disease and drug domains | F1 | Mixed |
Closest papers by meaning
- Global Distant Supervision for Relation Extraction (AAAI 2016 · similarity 0.91)
- Distant IE by Bootstrapping Using Lists and Document Structure (AAAI 2016 · similarity 0.90)
- Distant Supervision for Relation Extraction with Linear Attenuation Simulation and Non-IID Relevance Embedding (AAAI 2019 · similarity 0.90)
- A Positive-Unlabeled Metric Learning Framework for Document-Level Relation Extraction with Incomplete Labeling (AAAI 2024 · similarity 0.87)
- Synergistic Anchored Contrastive Pre-training for Few-Shot Relation Extraction (AAAI 2024 · similarity 0.86)
- 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.