Semantic Scaffolds for Pseudocode-to-Code Generation

05/12/2020
by   Ruiqi Zhong, et al.
0

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 pseudocode-to-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 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.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
02/16/2023

LEVER: Learning to Verify Language-to-Code Generation with Execution

The advent of large language models trained on code (code LLMs) has led ...
research
11/02/2018

Value-based Search in Execution Space for Mapping Instructions to Programs

Training models to map natural language instructions to programs given t...
research
06/12/2019

SPoC: Search-based Pseudocode to Code

We consider the task of mapping pseudocode to long programs that are fun...
research
03/06/2020

A Hierarchical Semantic Overlay for P2P Search

In this paper, we propose a hierarchical semantic overlay network for se...
research
10/12/2021

Program Transfer and Ontology Awareness for Semantic Parsing in KBQA

Semantic parsing in KBQA aims to parse natural language questions into l...
research
02/21/2018

Learning to Synthesize

In many scenarios we need to find the most likely program under a local ...
research
12/20/2022

Execution-Based Evaluation for Open-Domain Code Generation

To extend the scope of coding queries to more realistic settings, we pro...

Please sign up or login with your details

Forgot password? Click here to reset