Skip to main content

Code completion with statistical language models

Veselin Raychev, Martin T. Vechev, Eran Yahav

DOI 10.1145/2594291.2594321 dblp BibTeX

Abstract

We address the problem of synthesizing code completions for programs using APIs. Given a program with holes, we synthesize completions for holes with the most likely sequences of method calls.

Related papers

Probabilistic model for code with decision trees OOPSLA 2016
Automatic Inference of Models for Statistical Code Compression PLDI 1999
A domain theory for statistical probabilistic programming POPL 2019
AutoBayes: a system for generating data analysis programs from statistical models JFP 2003
Using web corpus statistics for program analysis OOPSLA 2014
An empirical investigation of the effects of type systems and code completion on API usability using TypeScript and JavaScript in MS visual studio DLS 2015
On the Impact of Programming Languages on Code Quality: A Reproduction Study TOPLAS 2019
Combining phase identification and statistic modeling for automated parallel benchmark generation PPoPP 2015