A deep language model for software code

August 09, 2016 Β· Declared Dead Β· πŸ› Fast Software Encryption Workshop

πŸ‘» CAUSE OF DEATH: Ghosted
No code link whatsoever

"No code URL or promise found in abstract"

Evidence collected by the PWNC Scanner

Authors Hoa Khanh Dam, Truyen Tran, Trang Pham arXiv ID 1608.02715 Category cs.SE: Software Engineering Cross-listed stat.ML Citations 112 Venue Fast Software Encryption Workshop Last Checked 3 months ago
Abstract
Existing language models such as n-grams for software code often fail to capture a long context where dependent code elements scatter far apart. In this paper, we propose a novel approach to build a language model for software code to address this particular issue. Our language model, partly inspired by human memory, is built upon the powerful deep learning-based Long Short Term Memory architecture that is capable of learning long-term dependencies which occur frequently in software code. Results from our intrinsic evaluation on a corpus of Java projects have demonstrated the effectiveness of our language model. This work contributes to realizing our vision for DeepSoft, an end-to-end, generic deep learning-based framework for modeling software and its development process.
Community shame:
Not yet rated
Community Contributions

Found the code? Know the venue? Think something is wrong? Let us know!

πŸ“œ Similar Papers

In the same crypt β€” Software Engineering

Died the same way β€” πŸ‘» Ghosted