AI Paper Atlas

Research map / Large language models / Agents, code and math

Program Synthesis and Semantic Parsing with Learned Code Idioms

Eui Chul Shin, Miltiadis Allamanis, Marc Brockschmidt, Alex Polozov

NeurIPS 2019 · Large language models › Agents, code and math · approach: LLM-guided program synthesis · 51 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 learned code idioms using the best reported configurationTree-based decoder · Hearthstone testExact match: 0.152 -> 0.197Improved
Add learned code idioms using the best reported configurationTree-based decoder · Hearthstone testSentence BLEU: 0.743 -> 0.780Improved
Add learned code idioms using the best reported configurationTree-based decoder · Hearthstone testCorpus BLEU: 0.723 -> 0.766Improved
Add learned code idioms ranked by Score_CXE with K=80Tree-based decoder · Spider devExact match: 0.395 -> 0.416Improved
Vary the idiom count and ranking method (Score_Cov or Score_CXE; K=10, 20, 40, or 80) (ablation)Patois · Hearthstone devExact match: 0.197; 0.151, 0.091, 0.167, 0.197; 0.151, 0.167, 0.182, 0.151Mixed
Vary the idiom count and ranking method (Score_Cov or Score_CXE; K=10, 20, 40, or 80) (ablation)Patois · Hearthstone devSentence BLEU: 0.767; 0.781, 0.745, 0.765, 0.780; 0.780, 0.787, 0.773, 0.771Mixed
Vary the idiom count and ranking method (Score_Cov or Score_CXE; K=10, 20, 40, or 80) (ablation)Patois · Hearthstone devCorpus BLEU: 0.763; 0.785, 0.745, 0.764, 0.774; 0.783, 0.782, 0.770, 0.768Mixed
Vary the idiom count and ranking method (Score_Cov or Score_CXE; K=10, 20, 40, or 80) (ablation)Patois · Spider devExact match: 0.395; 0.394, 0.379, 0.395, 0.407; 0.368, 0.382, 0.387, 0.416Mixed

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