AI Paper Atlas

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

Automatic Generation of Text Descriptive Comments for Code Blocks

Yuding Liang, Kenny Zhu

AAAI 2018 · Image generation › Text-to-image diffusion · approach: Text generation and structured prediction · 108 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
replace the Basic RNN cell with Code-GRU while using Code-RNN method vectorscomment generation · neo4jROUGE-2: 0.133 -> 0.141Improved
replace the Basic RNN cell with Code-GRU while using Code-RNN method vectorscomment generation · cocos2dROUGE-2: 0.152 -> 0.158Improved
replace the Basic RNN cell with Code-GRU while using Code-RNN method vectorscomment generation · jerseyROUGE-2: 0.214 -> 0.230Improved
replace the Basic RNN cell with Code-GRU while using Code-RNN method vectorscomment generation · aima-javaROUGE-2: 0.207 -> 0.209Improved
replace the Basic RNN cell with Code-GRU while using Code-RNN method vectorscomment generation · guavaROUGE-2: 0.156 -> 0.164Improved
replace the Basic RNN cell with Code-GRU while using Code-RNN method vectorscomment generation · SmackROUGE-2: 0.150 -> 0.162Improved
replace the Basic RNN cell with Code-GRU while using Code-RNN method vectorscomment generation · ActivitiROUGE-2: 0.203 -> 0.200Hurt
replace the Basic RNN cell with Code-GRU while using Code-RNN method vectorscomment generation · spring-batchROUGE-2: 0.237 -> 0.213Hurt
replace the Basic RNN cell with Code-GRU while using Code-RNN method vectorscomment generation · libgdxROUGE-2: 0.218 -> 0.233Improved
replace the Basic RNN cell with Code-GRU while using Code-RNN method vectorscomment generation · rhinoROUGE-2: 0.163 -> 0.165Hurt
use Code-RNN average tree composition rather than language embedding averagesource-code classification · Google Code Jam 6-class testF1: 0.3515 -> 0.4774Improved
use Code-RNN average tree composition rather than language embedding averagesource-code classification · Google Code Jam 6-class testAccuracy: 0.3667 -> 0.5Improved

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