SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2005.05927 · ACL · 2020

Semantic Scaffolds for Pseudocode-to-Code Generation

Dan Klein, Ruiqi Zhong, Mitchell Stern

arXiv · PDF · Open in the Atlas

Code that ran

We have not lifted any functions out of this paper's repositories yet, so there is nothing we have run. The repositories linked to it are listed below.

Repositories linked to this paper

Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.

Abstract

We propose a method for program generation based on semantic scaffolds, lightweight structures representing the high-level semantic and syntactic composition of a program. By first searching over plausible scaffolds then using these as constraints for a beam search over programs, we achieve better coverage of the search space when compared with existing techniques. We apply our hierarchical search method to the SPoC dataset for pseudocodeto-code generation, in which we are given line-level natural language pseudocode annotations and aim to produce a program satisfying execution-based test cases. By using semantic scaffolds during inference, we achieve a 10% absolute improvement in top-100 accuracy over the previous state-of-the-art. Additionally, we require only 11 candidates to reach the top-3000 performance of the previous best approach when tested against unseen problems, demonstrating a substantial improvement in efficiency.

For agents

The same record, over MCP at https://syntology.ai/mcp:

get_harvested_code_for_paper("2005.05927")
get_code_for_paper("2005.05927")
have("2005.05927")

The run record, dated, one paper per request, free:

curl https://syntology.ai/api/ran/2005.05927.json

A badge for a README (the split and the date, never a ratio):

[![Syntology run record](https://syntology.ai/api/ran/2005.05927.svg)](https://syntology.ai/paper/2005.05927)

Connect an agent — have() is free.