A deep language model for software code

Dam, Hoa Khanh, Tran, Truyen and Pham, Trang Thi Minh 2016, A deep language model for software code, in FSE 2016 : Proceedings of the Foundations Software Engineering International Symposium, [The Conference], [Seattle, Washington], pp. 1-4.

Attached Files
Name Description MIMEType Size Downloads

Title A deep language model for software code
Author(s) Dam, Hoa Khanh
Tran, TruyenORCID iD for Tran, Truyen orcid.org/0000-0001-6531-8907
Pham, Trang Thi Minh
Conference name Foundations of Software Engineering. International Symposium (2016 : Seattle, Washington)
Conference location Seattle, Washington
Conference dates 2016/11/11 - 2016/11/11
Title of proceedings FSE 2016 : Proceedings of the Foundations Software Engineering International Symposium
Publication date 2016
Start page 1
End page 4
Total pages 4
Publisher [The Conference]
Place of publication [Seattle, Washington]
Summary Existing language models such as n-grams for software codeoften fail to capture a long context where dependent codeelements scatter far apart. In this paper, we propose a novelapproach to build a language model for software code toaddress this particular issue. Our language model, partlyinspired by human memory, is built upon the powerful deeplearning-based Long Short Term Memory architecture thatis capable of learning long-term dependencies which occurfrequently in software code. Results from our intrinsic eval-uation on a corpus of Java projects have demonstrated thee ectiveness of our language model. This work contributesto realizing our vision for DeepSoft, an end-to-end, genericdeep learning-based framework for modeling software and itsdevelopment process.
Language eng
Field of Research 080308 Programming Languages
Socio Economic Objective 0 Not Applicable
HERDC Research category E2 Full written paper - non-refereed / Abstract reviewed
ERA Research output type X Not reportable
Copyright notice ©2016, ACM
Persistent URL http://hdl.handle.net/10536/DRO/DU:30096795

Connect to link resolver
Unless expressly stated otherwise, the copyright for items in DRO is owned by the author, with all rights reserved.

Version Filter Type
Citation counts: TR Web of Science Citation Count  Cited 0 times in TR Web of Science
Scopus Citation Count Cited 0 times in Scopus
Google Scholar Search Google Scholar
Access Statistics: 71 Abstract Views, 6 File Downloads  -  Detailed Statistics
Created: Tue, 30 May 2017, 16:44:42 EST

Every reasonable effort has been made to ensure that permission has been obtained for items included in DRO. If you believe that your rights have been infringed by this repository, please contact drosupport@deakin.edu.au.