Skip to main content
placeholder image

DeepSoft: A Vision for a Deep Model of Software

Conference Paper


Abstract


  • Although software analytics has experienced rapid growth

    as a research area, it has not yet reached its full potential

    for wide industrial adoption. Most of the existing work

    in software analytics still relies heavily on costly manual

    feature engineering processes, and they mainly address the

    traditional classification problems, as opposed to predicting

    future events. We present a vision for DeepSoft, an endto-end

    generic framework for modeling software and its development

    process to predict future risks and recommend

    interventions. DeepSoft, partly inspired by human memory,

    is built upon the powerful deep learning-based Long Short

    Term Memory architecture that is capable of learning longterm

    temporal dependencies that occur in software evolution.

    Such deep learned patterns of software can be used to

    address a range of challenging problems such as code and

    task recommendation and prediction. DeepSoft provides a

    new approach for research into modeling of source code, risk

    prediction and mitigation, developer modeling, and automatically

    generating code patches from bug reports.

UOW Authors


Publication Date


  • 2016

Citation


  • Dam, H. Khanh., Tran, T., Ghose, A. & Grundy, J. (2016). DeepSoft: A Vision for a Deep Model of Software. In T. Zimmermann, J. Cleland-Huang & Z. Su (Eds.), 24th ACM SIGSOFT International Symposium on the Foundations of Software Engineering (FSE 2016) (pp. 944-947). United States: ACM.

Scopus Eid


  • 2-s2.0-84997497811

Ro Metadata Url


  • http://ro.uow.edu.au/eispapers1/412

Start Page


  • 944

End Page


  • 947

Place Of Publication


  • United States

Abstract


  • Although software analytics has experienced rapid growth

    as a research area, it has not yet reached its full potential

    for wide industrial adoption. Most of the existing work

    in software analytics still relies heavily on costly manual

    feature engineering processes, and they mainly address the

    traditional classification problems, as opposed to predicting

    future events. We present a vision for DeepSoft, an endto-end

    generic framework for modeling software and its development

    process to predict future risks and recommend

    interventions. DeepSoft, partly inspired by human memory,

    is built upon the powerful deep learning-based Long Short

    Term Memory architecture that is capable of learning longterm

    temporal dependencies that occur in software evolution.

    Such deep learned patterns of software can be used to

    address a range of challenging problems such as code and

    task recommendation and prediction. DeepSoft provides a

    new approach for research into modeling of source code, risk

    prediction and mitigation, developer modeling, and automatically

    generating code patches from bug reports.

UOW Authors


Publication Date


  • 2016

Citation


  • Dam, H. Khanh., Tran, T., Ghose, A. & Grundy, J. (2016). DeepSoft: A Vision for a Deep Model of Software. In T. Zimmermann, J. Cleland-Huang & Z. Su (Eds.), 24th ACM SIGSOFT International Symposium on the Foundations of Software Engineering (FSE 2016) (pp. 944-947). United States: ACM.

Scopus Eid


  • 2-s2.0-84997497811

Ro Metadata Url


  • http://ro.uow.edu.au/eispapers1/412

Start Page


  • 944

End Page


  • 947

Place Of Publication


  • United States