Research map / Label-efficient and robust learning / Recognition and long-tail
Neural Relation Extraction within and across Sentence Boundaries
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 iDepNN-ADP instead of graphLSTM | relation extraction · BioNLP ST 2016, train and evaluation k ≤ 1 | F1: .336 -> .449 | Helped |
| use iDepNN-ADP instead of iDepNN-SDP (ablation) | relation extraction · BioNLP ST 2016, train and evaluation k ≤ 1 | F1: .435 -> .449 | Helped |
| add dependency subtrees to the iSDP representation (ablation) | iDepNN on BioNLP ST 2016 · BioNLP ST 2016, inter-sentential k ≤ 1 | F1: .431 -> .449 | Helped |
| add position indicators and entity types to iSDP (ablation) | iDepNN on BioNLP ST 2016 · BioNLP ST 2016, inter-sentential k ≤ 1 | F1: .436 -> .432 | Hurt |
| add POS features after PI and entity types (ablation) | iDepNN on BioNLP ST 2016 · BioNLP ST 2016, inter-sentential k ≤ 1 | F1: .432 -> .431 | Hurt |
| add dependency subtrees to the iSDP representation (ablation) | iDepNN on MUC6 · MUC6, inter-sentential k ≤ 1 | F1: .926 -> .935 | Helped |
| add position indicators to iSDP (ablation) | iDepNN on MUC6 · MUC6, inter-sentential k ≤ 1 | F1: .913 -> .909 | Hurt |
| add POS features after position indicators (ablation) | iDepNN on MUC6 · MUC6, inter-sentential k ≤ 1 | F1: .909 -> .926 | Helped |
| train the ensemble and retain predictions with p ≥ 0.85 | BioNLP ST 2016 ensemble · BioNLP ST 2016 test | F1: .478 -> .530 | Helped |
Closest papers by meaning
- SEE: Syntax-Aware Entity Embedding for Neural Relation Extraction (AAAI 2018 · similarity 0.89)
- Integrating Relation Constraints with Neural Relation Extractors (AAAI 2020 · similarity 0.88)
- Large Scaled Relation Extraction With Reinforcement Learning (AAAI 2018 · similarity 0.87)
- Aggregating Inter-Sentence Information to Enhance Relation Extraction (AAAI 2016 · similarity 0.87)
- Enhancing Low-Resource Relation Representations through Multi-View Decoupling (AAAI 2024 · similarity 0.84)
- DocKS-RAG: Optimizing Document-Level Relation Extraction through LLM-Enhanced Hybrid Prompt Tuning (ICML 2025 · similarity 0.84)
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.