Research map / Architectures and efficiency / Attention and transformers
Selecting Optimal Context Sentences for Event-Event 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 |
|---|---|---|---|
| select important context sentences with learned sequential selection | RoBERTa event-event relation extraction · HiEve test | F1 (micro-average): 62.8 -> 65.9 | Helped |
| select important context sentences with learned sequential selection | RoBERTa temporal event relation extraction · MATRES test | F1: 82.3 -> 83.4 | Helped |
| select important context sentences with learned sequential selection | RoBERTa temporal event relation extraction · TDDMan test | F1: 45.5 -> 51.1 | Helped |
| select important context sentences with learned sequential selection | RoBERTa temporal event relation extraction · TDDAuto test | F1: 71.1 -> 76.7 | Helped |
| add multi-step LSTM-based sentence selection conditioned on previously selected sentences (ablation) | SCS-EERE · MATRES test | F1: 80.4 -> 83.4 | Helped |
| add multi-step LSTM-based sentence selection conditioned on previously selected sentences (ablation) | SCS-EERE · HiEve test | F1 (micro-average): 60.4 -> 65.9 | Helped |
| add performance-based reward (ablation) | SCS-EERE · MATRES test | F1: 80.9 -> 83.4 | Helped |
| add performance-based reward (ablation) | SCS-EERE · HiEve test | F1 (micro-average): 63.4 -> 65.9 | Helped |
| add context-based reward (ablation) | SCS-EERE · MATRES test | F1: 81.0 -> 83.4 | Helped |
| add context-based reward (ablation) | SCS-EERE · HiEve test | F1 (micro-average): 64.2 -> 65.9 | Helped |
| add knowledge-based reward (ablation) | SCS-EERE · MATRES test | F1: 81.2 -> 83.4 | Helped |
| add knowledge-based reward (ablation) | SCS-EERE · HiEve test | F1 (micro-average): 62.5 -> 65.9 | Helped |
Closest papers by meaning
- Logic Induced High-Order Reasoning Network for Event-Event Relation Extraction (AAAI 2025 · similarity 0.89)
- SEFEL: A Simple Yet Effective Framework for Fast Event Linking (AAAI 2026 · similarity 0.88)
- Hierarchical Event Grounding (AAAI 2023 · similarity 0.87)
- A Hierarchical Network for Multimodal Document-Level Relation Extraction (AAAI 2024 · similarity 0.86)
- A Joint Framework with Heterogeneous-Relation-Aware Graph and Multi-Channel Label Enhancing Strategy for Event Causality Extraction (AAAI 2024 · similarity 0.86)
- Is a Large Language Model a Good Annotator for Event Extraction? (AAAI 2024 · 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.