A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2017; you can also visit the original URL.
The file type is application/pdf.
Multi-token code suggestions using statistical language models
[post]
2015
PeerJ Preprints
Preserved Fulltext
We present an application of the naturalness of software to provide multi-token code suggestions in GitHub's Atom text editor. We extended the results of a simple n-gram prediction model using the "mean surprise" metric—the arithmetic mean of the surprisal of several successive single-token predictions. After an error-fraught evaluation, there is not enough evidence to conclude that Gamboge significantly improves programmer productivity. We conclude by discussing several directions for future
doi:10.7287/peerj.preprints.1597v1
dblp:journals/peerjpre/SantosH15
fatcat:tzajo72tejbqrpcmhgzcgrvkbu