ACM Home Page
Please provide us with feedback. Feedback
Digital Library logoTake a look at the new version of this page: [ beta version ]. Tell us what you think.
Learning from examples to improve code completion systems
Full text PdfPdf (1.19 MB)
Source
Foundations of Software Engineering archive
Proceedings of the the 7th joint meeting of the European software engineering conference and the ACM SIGSOFT symposium on The foundations of software engineering table of contents
Amsterdam, The Netherlands
SESSION: Tools & environment table of contents
Pages: 213-222  
Year of Publication: 2009
ISBN:978-1-60558-001-2
Authors
Marcel Bruch  Darmstadt University of Technology, Darmstadt, Germany
Martin Monperrus  Darmstadt University of Technology, Darmstadt, Germany
Mira Mezini  Darmstadt University of Technology, Darmstadt, Germany
Sponsors
ACM: Association for Computing Machinery
SIGSOFT: ACM Special Interest Group on Software Engineering
Publisher
ACM  New York, NY, USA
Bibliometrics
Downloads (6 Weeks): 28,   Downloads (12 Months): 127,   Citation Count: 0
Additional Information:

abstract   references   index terms   collaborative colleagues  

Tools and Actions: Request Permissions Request Permissions    Review this Article  
DOI Bookmark: Use this link to bookmark this Article: http://doi.acm.org/10.1145/1595696.1595728
What is a DOI?

ABSTRACT

The suggestions made by current IDE's code completion features are based exclusively on static type system 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.


REFERENCES

Note: OCR errors may be found in this Reference List extracted from the full text article. ACM has opted to expose the complete List rather than only correct and linked references.

 
1
Overview of the Third Text REtrieval Conference (TREC-3), Gaithersburg, MD, USA, 1990. NIST.
2
 
3
 
4
5
6
7
 
8
T. Cover and P. Hart. Nearest neighbor pattern classification. IEEE Transactions on Information Theory, 1967.
 
9
Eclipse Foundation. SWT: The standard widget toolkit. http://www.eclipse.org/swt/, 2006.
10
 
11
D. Gangopadhyay and S. Mitra. Design by framework completion. Automated Software Eng., 3(3/4):219--237, 1996.
 
12
Google code search. http://www.google.com/codesearch.
 
13
14
15
16
 
17
Koders. http://www.koders.com.
 
18
19
20
 
21
 
22
23
 
24
25
 
26
27

Collaborative Colleagues:
Marcel Bruch: colleagues
Martin Monperrus: colleagues
Mira Mezini: colleagues