TU Darmstadt / ULB / TUbiblio

Learning from Examples to Improve Code Completion Systems

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

Kurzbeschreibung (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.

Typ des Eintrags: Konferenz- oder Workshop-Beitrag (Keine Angabe)
Erschienen: 2009
Autor(en): Bruch, Marcel ; Monperrus, Martin ; Mezini, Mira
Titel: Learning from Examples to Improve Code Completion Systems
Sprache: Englisch
Kurzbeschreibung (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.

Buchtitel: Proceedings of 17th ACM SIGSOFT Symposium on the Foundations of Software Engineering
Fachbereich(e)/-gebiet(e): Fachbereich Informatik > Softwaretechnik
Fachbereich Informatik
Veranstaltungstitel: 17th ACM SIGSOFT Symposium on the Foundations of Software Engineering (FSE-17)
Veranstaltungsort: Amsterdam , Netherlands
Veranstaltungsdatum: 24.-28. Aug 2009
Hinterlegungsdatum: 10 Jul 2009 12:33
Export:

Optionen (nur für Redakteure)

Eintrag anzeigen Eintrag anzeigen