2015 · 35 citations · 10 references
ComputingComputer ScienceNatural Language ProcessingProgramming LanguagesSoftware EngineeringLanguage ModelingStatistical Software DevelopmentSuggestion SystemsType SystemsIntegrated Development EnvironmentsLanguage Model IntegrationPatterns
includes a form of code completion. The suggested completions (“suggestions”) are typically based on information available at compile time, such as type signatures and variables in scope. A statistical approach, based on estimated models of code patterns in large code corpora, has been demonstrated to be effective at predicting tokens given a context. In this demo, we present CACHECA, an Eclipse plugin that combines the native suggestions with a statistical suggestion regime. We demonstrate that a combination of the two approaches more than doubles Eclipse’s suggestion accuracy. A video demonstration is available at
10
On the naturalness of software
Abram Hindle, Earl T. Barr, Zhendong Su et al. · 2012 · 569 citations
On the naturalness of software
Abram Hindle, Earl T. Barr, Zhendong Su et al. · 2012 · 418 citations
Learning from examples to improve code completion systems
Marcel Bruch, Martin Monperrus, Mira Mezini · 2009 · 379 citations · Full text
Zhaopeng Tu, Zhendong Su, Prémkumar Dévanbu · 2014 · 244 citations
A statistical semantic language model for source code
Tung Nguyen, Anh Tuan Nguyen, Hoan Anh Nguyen et al. · 2013 · 223 citations