AI Paper Atlas

Research map / Image generation / Text-to-image diffusion

Open Domain Event Text Generation

Zihao Fu, Lidong Bing, Wai Lam

AAAI 2020 · Image generation › Text-to-image diffusion · approach: Text generation and structured prediction · 8 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
add random drop (RD) of retrieved words during training (ablation)WAG · WikiEvent testBLEU: 0.231 -> 0.238Improved
add random drop (RD) (ablation)WAG · WikiEvent testCIDEr: 1.69 -> 1.76Improved
add random drop to S2S-E-W-2 inputS2S-E-W-2 · WikiEvent testROUGE-L: 0.385 -> 0.394Improved
add retrieved Wikipedia text to entity chain input (concatenation)S2S-E · WikiEvent testBLEU: 0.200 -> 0.224Improved
use retrieved text only, drop the entity chain skeletonS2S · WikiEvent testBLEU: 0.200 -> 0.157Hurt
replace concatenation with decoder-side attention over retrieved text (WAG)S2S-E-W-2' · WikiEvent testBLEU: 0.224 -> 0.238Improved
retrieve more than 1-2 sentences per entity (ablation)WAG · WikiEvent devBLEUHurt
distance-based drop instead of uniform random dropS2S-E-W-2 · WikiEvent testBLEU: 0.224 -> 0.231Mixed

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