Statistical Learning of API Fully Qualified Names in Code Snippets of Online Forums

Simple item page
dc.contributor.authorPhan, H.
dc.contributor.authorNguyen, H. A.
dc.contributor.authorTran, Ngoc M.
dc.contributor.authorTruong, Linh H.
dc.contributor.authorNguyen, A. T.
dc.contributor.authorNguyen, Tien N.
dc.contributor.utdAuthorTran, Ngoc M.
dc.contributor.utdAuthorTruong, Linh H.
dc.contributor.utdAuthorNguyen, Tien N.
dc.date.accessioned2019-09-27T16:05:18Z
dc.date.available2019-09-27T16:05:18Z
dc.date.created2018-05-27
dc.descriptionFull text access from Treasures at UT Dallas is restricted to current UTD affiliates (use the provided Link to Article).
dc.description.abstractSoftware developers often make use of the online forums such as StackOverflow (SO) to learn how to use software libraries and their APIs. However, the code snippets in such a forum often contain undeclared, ambiguous, or largely unqualified external references. Such declaration ambiguity and external reference ambiguity present challenges for developers in learning to correctly use the APIs. In this paper, we propose StatType, a statistical approach to resolve the fully qualified names (FQNs) for the API elements in such code snippets. Unlike existing approaches that are based on heuristics, StatType has two well-integrated factors. We first learn from a large training code corpus the FQNs that often co-occur. Then, to derive the FQN for an API name in a code snippet, we use that knowledge and also leverage the context consisting of neighboring API names. To realize those factors, we treat the problem as statistical machine translation from source code with partially qualified names to source code with FQNs of the APIs. Our empirical evaluation on real-world code and StackOverflow posts shows that StatType achieves very high accuracy with 97.6% precision and 96.7% recall, which is 16.5% relatively higher than the state-of-the-art approach. © 2018 ACM.
dc.description.departmentErik Jonsson School of Engineering and Computer Science
dc.description.sponsorship"This work was supported in part by the US National Science Foundation (NSF) grants CCF-1723215, CCF-1723432, TWC-1723198, CCF-1518897, and CNS-1513263."
dc.identifier.bibliographicCitationPhan, H., H. A. Nguyen, N. M. Tran, L. H. Truong, et al. 2018. "Statistical learning of API fully qualified names in code snippets of online forums." International Conference on Software Engineering, 40th 137142: 632-642, doi: 10.1145/3180155.3180230
dc.identifier.issn9781450356381
dc.identifier.urihttps://hdl.handle.net/10735.1/6917
dc.identifier.volume137142
dc.language.isoen
dc.publisherIEEE Computer Society
dc.relation.isPartOfInternational Conference on Software Engineering, 40th
dc.relation.urihttp://dx.doi.org/10.1145/3180155.3180230
dc.rights©2018 ACM
dc.subjectComputational linguistics
dc.subjectTranslator Writing Tools (Electronic computer system)
dc.subjectComputer programming
dc.subjectComputer-assisted instruction
dc.subjectKnowledge management
dc.subjectTranslators (Computer programs)--Design and construction
dc.subjectOnline social networks
dc.subjectComputer programs--Analysis
dc.subjectElectronic discussion groups--StackOverflow
dc.subjectComputer programs--StatType
dc.titleStatistical Learning of API Fully Qualified Names in Code Snippets of Online Forums
dc.type.genrearticle

Files

Original bundle

Now showing 1 - 1 of 1
Thumbnail Image
Name:
JECS-6853-260103.50-LINK.pdf
Size:
164.96 KB
Format:
Adobe Portable Document Format
Description:
Link to Article
Download

Collections

Nguyen, Tien N.