TU Darmstadt / ULB / TUbiblio

Learning from Examples to Improve Code Completion Systems

Bruch, Marcel and Monperrus, Martin and Mezini, Mira (2009):
Learning from Examples to Improve Code Completion Systems.
In: Proceedings of 17th ACM SIGSOFT Symposium on the Foundations of Software Engineering, In: 17th ACM SIGSOFT Symposium on the Foundations of Software Engineering (FSE-17), Amsterdam , Netherlands, 24.-28. Aug 2009, [Conference or Workshop Item]

Abstract

The suggestions made by current IDE’s code completion features are based exclusively on static properties of the programming language. As a result, often proposals are made which are irrelevant for a particular working context. Also, these suggestions are ordered alphabetically rather than by their relevance in a particular context. In this paper, we present intelligent code completion systems that learn from existing code repositories. We have implemented three such systems, each using the information contained in repositories in a different way. We perform a large-scale quantitative evaluation of these systems, integrate the best performing one into Eclipse, and evaluate the latter also by a user study. Our experiments give evidence that intelligent code completion systems which learn from examples significantly outperform mainstream code completion systems in terms of the relevance of their suggestions and thus have the potential to enhance developers’ productivity.

Item Type: Conference or Workshop Item
Erschienen: 2009
Creators: Bruch, Marcel and Monperrus, Martin and Mezini, Mira
Title: Learning from Examples to Improve Code Completion Systems
Language: English
Abstract:

The suggestions made by current IDE’s code completion features are based exclusively on static properties of the programming language. As a result, often proposals are made which are irrelevant for a particular working context. Also, these suggestions are ordered alphabetically rather than by their relevance in a particular context. In this paper, we present intelligent code completion systems that learn from existing code repositories. We have implemented three such systems, each using the information contained in repositories in a different way. We perform a large-scale quantitative evaluation of these systems, integrate the best performing one into Eclipse, and evaluate the latter also by a user study. Our experiments give evidence that intelligent code completion systems which learn from examples significantly outperform mainstream code completion systems in terms of the relevance of their suggestions and thus have the potential to enhance developers’ productivity.

Title of Book: Proceedings of 17th ACM SIGSOFT Symposium on the Foundations of Software Engineering
Divisions: 20 Department of Computer Science > Software Technology
20 Department of Computer Science
Event Title: 17th ACM SIGSOFT Symposium on the Foundations of Software Engineering (FSE-17)
Event Location: Amsterdam , Netherlands
Event Dates: 24.-28. Aug 2009
Date Deposited: 10 Jul 2009 12:33
Export:

Optionen (nur für Redakteure)

View Item View Item