AI Paper Atlas

Research map / Large language models / Language, safety and interpretability

Convolutional Neural Networks over Tree Structures for Programming Language Processing

AAAI 2016 · Large language models › Language, safety and interpretability · approach: Linguistic encoding in LLM representations · 536 citations (OpenAlex)

Read the paperCheck your idea against 108,967 papers

AI-extracted summary. Written by AI from the paper's title only (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 coding layer (ablation)TBCNN · 104-class program classification (validation)validation accuracy: 92.3 -> 94.4Helped
use continuous binary tree instead of CBoW child averaging (ablation)TBCNN · 104-class program classification (validation)validation accuracy: 93.1 -> 94.4Helped
use 3-way pooling instead of 1-way (ablation)TBCNN · 104-class program classification (validation)validation accuracy: 94.4 -> 94.3No clear effect
add unsupervised pretraining of AST node embeddings (ablation)TBCNN · 104-class program classification (OJ)accuracyNo clear effect
add unsupervised pretraining of AST node embeddings (ablation)TBCNN · 104-class program classification (OJ)training speed: nearly $1/3$Helped
tree-based convolution vs recursive NNprogram classification · 104-class program classification (OJ)test accuracy: 84.8 -> 94.0Helped
TBCNN vs RBF SVM with bag-of-treesbubble sort detection · bubble sort detectionaccuracy: 77.1 -> 89.1Helped

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