AI Paper Atlas

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

NeurIPS 2021 · Graph learning › Knowledge and temporal graphs · approach: Temporal knowledge graph reasoning · 0 citations (OpenAlex)

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 changedWhereMeasuredEffect
use BART-base instead of T5-baseKG-to-text PLM · EventNarrative testBLEU: 12.8 -> 31.38Improved
use BART-base instead of T5-baseKG-to-text PLM · EventNarrative testchrF++: 56.76 -> 64.71Improved
use BART-base instead of T5-baseKG-to-text PLM · EventNarrative testROUGE-L: 52.06 -> 62.65Improved
use BART-base instead of T5-baseKG-to-text PLM · EventNarrative testBERTScore: 89.59 -> 93.12Improved
use graph-specific GraphWriter instead of BART-baseKG-to-text model · EventNarrative testROUGE-L: 62.65 -> 71.92Improved
use graph-specific GraphWriter instead of BART-baseKG-to-text model · EventNarrative testCIDEr: 3.31 -> 4.59Improved
use graph-specific GraphWriter instead of BART-baseKG-to-text model · EventNarrative testMETEOR: 26.68 -> 27.72Improved
use graph-specific GraphWriter instead of BART-baseKG-to-text model · EventNarrative testBLEU: 31.38 -> 30.78No clear effect
use graph-specific GraphWriter instead of BART-baseKG-to-text model · EventNarrative testchrF++: 64.71 -> 47.91Hurt
use GraphWriter instead of T5-baseKG-to-text model · EventNarrative testBLEU: 12.8 -> 30.78Improved
use date matching with month/year overlap fallback in entity matchingdataset creation · EventNarrative datasetpair filteringNo clear effect
filter pairs without entity matchesdataset creation · EventNarrative datasetKG-text pairs: 316,281 -> 315,724Mixed

Closest papers by meaning

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.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy