CACHECA: A Cache Language Model Based Code Suggestion Tool
Authors:
- Christine FranksCFChristine Franks
- Zhaopeng TuZTZhaopeng Tu
- Premkumar DevanbuPDPremkumar Devanbu
- Vincent HellendoornVHVincent Hellendoorn
- 1 May 2015
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- Vol. 2 (02705257) , 705-708
Abstract
Nearly every Integrated Development Environment 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 plug in 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 https://www.youtube.com/watch?v=3INk0N3JNtc.Keywords
This publication has 8 references indexed in Scilit:
- On the localness of software2014
- A statistical semantic language model for source code2013
- On the naturalness of software2012
- Graph-based pattern-oriented, context-sensitive source code completion2012
- IDE 2.02010
- Calcite: Completing Code Completion for Constructors Using Crowds2010
- Improving code completion with program historyAutomated Software Engineering, 2010
- Learning from examples to improve code completion systems2009