Research map / Label-efficient and robust learning / Recognition and long-tail
Aggregating Inter-Sentence Information to Enhance Relation Extraction
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 |
|---|---|---|---|
| add global cross-entity-pair ranking constraints to RankRE (ablation) | RankRE-local · KBP precision-recall curve, low recall | precision | Helped |
| add global ranking constraints (ablation) | RankRE-local · KBP multi-instance subset | precision top-50: 0.580 -> 0.560 | Hurt |
| add global ranking constraints (ablation) | RankRE-local · KBP multi-instance subset | precision top-150: 0.426 -> 0.433 | Helped |
| replace MIML-RE with RankRE-global (ranking, aggregating inter-sentence scores) | relation extraction on KBP · KBP multi-instance subset | precision top-150: 0.406 -> 0.433 | Helped |
| replace MIML-RE with RankRE-global | relation extraction on KBP · KBP full test, high-recall region (recall > 0.22) | precision: up to ~4 precision points lower | Hurt |
| use RankRE perceptron-style ranking instead of MIML-RE EM training | relation extraction on KBP · KBP | training time: 21 hours -> 6 minutes | Helped |
Closest papers by meaning
- Joint Extraction of Entities and Overlapping Relations Using Position-Attentive Sequence Labeling (AAAI 2019 · similarity 0.89)
- Distant Supervision for Relation Extraction with Sentence-Level Attention and Entity Descriptions (AAAI 2017 · similarity 0.89)
- Are Noisy Sentences Useless for Distant Supervised Relation Extraction? (AAAI 2020 · similarity 0.89)
- A Positive-Unlabeled Metric Learning Framework for Document-Level Relation Extraction with Incomplete Labeling (AAAI 2024 · similarity 0.88)
- DocKS-RAG: Optimizing Document-Level Relation Extraction through LLM-Enhanced Hybrid Prompt Tuning (ICML 2025 · similarity 0.86)
- Enhancing Relation Extraction via Supervised Rationale Verification and Feedback (AAAI 2025 · similarity 0.85)
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.