Research map / Image generation / Text-to-image diffusion
Automatic Generation of Text Descriptive Comments for Code Blocks
Yuding Liang, Kenny Zhu
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 |
|---|---|---|---|
| replace the Basic RNN cell with Code-GRU while using Code-RNN method vectors | comment generation · neo4j | ROUGE-2: 0.133 -> 0.141 | Improved |
| replace the Basic RNN cell with Code-GRU while using Code-RNN method vectors | comment generation · cocos2d | ROUGE-2: 0.152 -> 0.158 | Improved |
| replace the Basic RNN cell with Code-GRU while using Code-RNN method vectors | comment generation · jersey | ROUGE-2: 0.214 -> 0.230 | Improved |
| replace the Basic RNN cell with Code-GRU while using Code-RNN method vectors | comment generation · aima-java | ROUGE-2: 0.207 -> 0.209 | Improved |
| replace the Basic RNN cell with Code-GRU while using Code-RNN method vectors | comment generation · guava | ROUGE-2: 0.156 -> 0.164 | Improved |
| replace the Basic RNN cell with Code-GRU while using Code-RNN method vectors | comment generation · Smack | ROUGE-2: 0.150 -> 0.162 | Improved |
| replace the Basic RNN cell with Code-GRU while using Code-RNN method vectors | comment generation · Activiti | ROUGE-2: 0.203 -> 0.200 | Hurt |
| replace the Basic RNN cell with Code-GRU while using Code-RNN method vectors | comment generation · spring-batch | ROUGE-2: 0.237 -> 0.213 | Hurt |
| replace the Basic RNN cell with Code-GRU while using Code-RNN method vectors | comment generation · libgdx | ROUGE-2: 0.218 -> 0.233 | Improved |
| replace the Basic RNN cell with Code-GRU while using Code-RNN method vectors | comment generation · rhino | ROUGE-2: 0.163 -> 0.165 | Hurt |
| use Code-RNN average tree composition rather than language embedding average | source-code classification · Google Code Jam 6-class test | F1: 0.3515 -> 0.4774 | Improved |
| use Code-RNN average tree composition rather than language embedding average | source-code classification · Google Code Jam 6-class test | Accuracy: 0.3667 -> 0.5 | Improved |
Closest papers by meaning
- On-the-Fly Adapting Code Summarization on Trainable Cost-Effective Language Models (NeurIPS 2023 · similarity 0.85)
- A Grammar-Based Structural CNN Decoder for Code Generation (AAAI 2019 · similarity 0.85)
- code2seq: Generating Sequences from Structured Representations of Code (ICLR 2019 · similarity 0.85)
- Neural Code Comprehension: A Learnable Representation of Code Semantics (NeurIPS 2018 · similarity 0.85)
- Detecting AI-Generated Code Assignments Using Perplexity of Large Language Models (AAAI 2024 · similarity 0.83)
- AlchemistCoder: Harmonizing and Eliciting Code Capability by Hindsight Tuning on Multi-source Data (NeurIPS 2024 · similarity 0.83)
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.
