Research map / Graph learning / Knowledge and temporal graphs
EventNarrative: A Large-scale Event-centric Dataset for Knowledge Graph-to-Text Generation
Anthony Colas, Ali Sadeghian, Yue Wang, Daisy Zhe Wang
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (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 BART-base instead of T5-base | KG-to-text PLM · EventNarrative test | BLEU: 12.8 -> 31.38 | Improved |
| use BART-base instead of T5-base | KG-to-text PLM · EventNarrative test | chrF++: 56.76 -> 64.71 | Improved |
| use BART-base instead of T5-base | KG-to-text PLM · EventNarrative test | ROUGE-L: 52.06 -> 62.65 | Improved |
| use BART-base instead of T5-base | KG-to-text PLM · EventNarrative test | BERTScore: 89.59 -> 93.12 | Improved |
| use graph-specific GraphWriter instead of BART-base | KG-to-text model · EventNarrative test | ROUGE-L: 62.65 -> 71.92 | Improved |
| use graph-specific GraphWriter instead of BART-base | KG-to-text model · EventNarrative test | CIDEr: 3.31 -> 4.59 | Improved |
| use graph-specific GraphWriter instead of BART-base | KG-to-text model · EventNarrative test | METEOR: 26.68 -> 27.72 | Improved |
| use graph-specific GraphWriter instead of BART-base | KG-to-text model · EventNarrative test | BLEU: 31.38 -> 30.78 | No clear effect |
| use graph-specific GraphWriter instead of BART-base | KG-to-text model · EventNarrative test | chrF++: 64.71 -> 47.91 | Hurt |
| use GraphWriter instead of T5-base | KG-to-text model · EventNarrative test | BLEU: 12.8 -> 30.78 | Improved |
| use date matching with month/year overlap fallback in entity matching | dataset creation · EventNarrative dataset | pair filtering | No clear effect |
| filter pairs without entity matches | dataset creation · EventNarrative dataset | KG-text pairs: 316,281 -> 315,724 | Mixed |
Closest papers by meaning
- KGGen: Extracting Knowledge Graphs from Plain Text with Language Models (NeurIPS 2025 · similarity 0.88)
- EMERGE: A Benchmark for Updating Knowledge Graphs with Emerging Textual Knowledge (NeurIPS 2026 · similarity 0.86)
- Is a Large Language Model a Good Annotator for Event Extraction? (AAAI 2024 · similarity 0.86)
- TGB 2.0: A Benchmark for Learning on Temporal Knowledge Graphs and Heterogeneous Graphs (NeurIPS 2024 · similarity 0.86)
- STAR: Boosting Low-Resource Information Extraction by Structure-to-Text Data Generation with Large Language Models (AAAI 2024 · similarity 0.85)
- Logic Induced High-Order Reasoning Network for Event-Event Relation Extraction (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.
