2015
DOI: 10.7287/peerj.preprints.1597
|View full text |Cite
Preprint
|
Sign up to set email alerts
|

Multi-token code suggestions using statistical language models

Abstract: I present an application of the Naturalness of software to provide multitoken code suggestions in GitHub's new-fangled Atom text editor 1 . After an error-fraught evaluation, there is not enough evidence to conclude that Gamboge significantly improves programmer productivity. I conclude by discussing several directions for research in code suggestion using naturalness.

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...

Citation Types

0
0
0

Publication Types

Select...

Relationship

0
0

Authors

Journals

citations
Cited by 0 publications
references
References 3 publications
0
0
0
Order By: Relevance

No citations

Set email alert for when this publication receives citations?