TU Darmstadt / ULB / TUbiblio

Intelligent Code Completion with Bayesian Networks

Proksch, Sebastian ; Lerch, Johannes ; Mezini, Mira :
Intelligent Code Completion with Bayesian Networks.
[Online-Edition: http://doi.acm.org/10.1145/2744200]
In: ACM Transactions on Software Engineering and Methodology (TOSEM), 25 (1) 3:1-3:31.
[Artikel], (2015)

Offizielle URL: http://doi.acm.org/10.1145/2744200

Kurzbeschreibung (Abstract)

Code completion is an integral part of modern Integrated Development Environments (IDEs). Developers often use it to explore Application Programming Interfaces (APIs). It is also useful to reduce the required amount of typing and to help avoid typos. Traditional code completion systems propose all type-correct methods to the developer. Such a list is often very long with many irrelevant items. More intelligent code completion systems have been proposed in prior work to reduce the list of proposed methods to relevant items.

This work extends one of these existing approaches, the Best Matching Neighbor (BMN) algorithm. We introduce Bayesian networks as an alternative underlying model, use additional context information for more precise recommendations, and apply clustering techniques to improve model sizes. We compare our new approach, Pattern-based Bayesian Networks (PBN), to the existing BMN algorithm. We extend previously used evaluation methodologies and, in addition to prediction quality, we also evaluate model size and inference speed.

Our results show that the additional context information we collect improves prediction quality, especially for queries that do not contain method calls. We also show that PBN can obtain comparable prediction quality to BMN, while model size and inference speed scale better with large input sizes.

Typ des Eintrags: Artikel
Erschienen: 2015
Autor(en): Proksch, Sebastian ; Lerch, Johannes ; Mezini, Mira
Titel: Intelligent Code Completion with Bayesian Networks
Sprache: Englisch
Kurzbeschreibung (Abstract):

Code completion is an integral part of modern Integrated Development Environments (IDEs). Developers often use it to explore Application Programming Interfaces (APIs). It is also useful to reduce the required amount of typing and to help avoid typos. Traditional code completion systems propose all type-correct methods to the developer. Such a list is often very long with many irrelevant items. More intelligent code completion systems have been proposed in prior work to reduce the list of proposed methods to relevant items.

This work extends one of these existing approaches, the Best Matching Neighbor (BMN) algorithm. We introduce Bayesian networks as an alternative underlying model, use additional context information for more precise recommendations, and apply clustering techniques to improve model sizes. We compare our new approach, Pattern-based Bayesian Networks (PBN), to the existing BMN algorithm. We extend previously used evaluation methodologies and, in addition to prediction quality, we also evaluate model size and inference speed.

Our results show that the additional context information we collect improves prediction quality, especially for queries that do not contain method calls. We also show that PBN can obtain comparable prediction quality to BMN, while model size and inference speed scale better with large input sizes.

Titel der Zeitschrift, Zeitung oder Schriftenreihe: ACM Transactions on Software Engineering and Methodology (TOSEM)
Band: 25
(Heft-)Nummer: 1
Ort: New York, NY, USA
Verlag: ACM Press
Freie Schlagworte: Content assist, code completion, code recommender, evaluation, integrated development environments, machine learning, productivity
Fachbereich(e)/-gebiet(e): 20 Fachbereich Informatik
20 Fachbereich Informatik > Softwaretechnik
DFG-Sonderforschungsbereiche (inkl. Transregio)
DFG-Sonderforschungsbereiche (inkl. Transregio) > Sonderforschungsbereiche
DFG-Sonderforschungsbereiche (inkl. Transregio) > Sonderforschungsbereiche > SFB 1119: CROSSING – Kryptographiebasierte Sicherheitslösungen als Grundlage für Vertrauen in heutigen und zukünftigen IT-Systemen
Veranstaltungsort: New York, NY, USA
Hinterlegungsdatum: 29 Jan 2016 13:22
Offizielle URL: http://doi.acm.org/10.1145/2744200
Export:

Optionen (nur für Redakteure)

Eintrag anzeigen Eintrag anzeigen