Multi-token code suggestions using statistical language models [post]

Eddie A Santos, Abram Hindle
2015 PeerJ Preprints  
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
more » ... search in code suggestion and more using naturalness.
doi:10.7287/peerj.preprints.1597v1 dblp:journals/peerjpre/SantosH15 fatcat:tzajo72tejbqrpcmhgzcgrvkbu