AI Paper Atlas

Research map / Vision-language and multimodal / Human and embodied modeling

NS3: Neuro-symbolic Semantic Code Search

Shushan Arakelyan, Anna Hakhverdyan, Miltiadis Allamanis, Luis Antonio Garcia, Christophe Hauser, Xiang Ren

NeurIPS 2022 · Vision-language and multimodal › Human and embodied modeling · approach: Multimodal retrieval-augmented modeling · 2 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 NS³'s parse-driven modular re-ranking instead of GraphCodeBERT* re-rankingCodeSearchNet · CodeSearchNet testMRR: 0.883 -> 0.924Improved
Use NS³ instead of GraphCodeBERTCodeSearchNet with 10K training examples · CodeSearchNet-10K testMRR: 0.786 -> 0.826Improved
Use NS³ instead of GraphCodeBERTCodeSearchNet with 5K training examples · CodeSearchNet-5K testMRR: 0.773 -> 0.823Improved
Use NS³ instead of GraphCodeBERT* re-rankingCoSQA-trained model · WebQueryTestMRR: 0.462 -> 0.551Improved
Use NS³ with CodeBERT fallback for unparsable examples instead of GraphCodeBERTCoSQA-trained model · CoSQA full test setMRR: 0.367 -> 0.412Improved
Add action-module pretraining before end-to-end training (ablation)NS³ · CodeSearchNet testMRRImproved
Add both module pretraining procedures before end-to-end training (ablation)NS³ · CodeSearchNet testMRRImproved
Add end-to-end training after module pretraining (ablation)NS³ · CodeSearchNet testMRRImproved
Normalize module output scores (ablation)NS³ · CodeSearchNet and CoSQAMRRImproved
Normalize only action-module or only entity-discovery output rather than both (ablation)NS³ · CodeSearchNet and CoSQAMRRNo clear effect
Replace dot-product similarity with L2 distance or weighted cosine similarity (ablation)NS³ · CodeSearchNet testMRRNo clear effect

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