Standard

DeepAPI# : CLR/C# call sequence synthesis from text query. / Chebykin, Alexander; Kita, Mikhail; Kirilenko, Iakov.

In: CEUR Workshop Proceedings, Vol. 1864, 01.01.2017.

Research output: Contribution to journal › Conference article › peer-review

Harvard

Chebykin, A, Kita, M & Kirilenko, I 2017, 'DeepAPI#: CLR/C# call sequence synthesis from text query', CEUR Workshop Proceedings, vol. 1864.

APA

Chebykin, A., Kita, M., & Kirilenko, I. (2017). DeepAPI#: CLR/C# call sequence synthesis from text query. CEUR Workshop Proceedings, 1864.

Vancouver

Chebykin A, Kita M, Kirilenko I. DeepAPI#: CLR/C# call sequence synthesis from text query. CEUR Workshop Proceedings. 2017 Jan 1;1864.

Author

Chebykin, Alexander ; Kita, Mikhail ; Kirilenko, Iakov. / DeepAPI# : CLR/C# call sequence synthesis from text query. In: CEUR Workshop Proceedings. 2017 ; Vol. 1864.

BibTeX

@article{e29acdd4fe8e45c1b47c648059a18b75,
title = "DeepAPI#: CLR/C# call sequence synthesis from text query",
abstract = "Developers often search for an implementation of typical features via libraries (for example, how to create a UI button control, extract data from a JSON-formatted file, etc.). The Internet is the usual source of the information on the topic. However, various statistical tools provide an alternative: after processing large amounts of source code and learning common patterns, they can convert a user request to a set of relevant function calls. We examine one of those tools - DeepAPI. This fresh deep learning based algorithm outperforms all others (according to its authors). We attempt to reproduce this result using different target programming language - C# - instead of Java used in the original DeepAPI. In this paper we report arising problems in the data gathering for training, difficulties in the model construction and training, and finally discuss possible modifications of the algorithm.",
author = "Alexander Chebykin and Mikhail Kita and Iakov Kirilenko",
year = "2017",
month = jan,
day = "1",
language = "English",
volume = "1864",
journal = "CEUR Workshop Proceedings",
issn = "1613-0073",
publisher = "RWTH Aahen University",
note = "2nd Conference on Software Engineering and Information Management, SEIM 2017 ; Conference date: 21-04-2017",

}

RIS

TY - JOUR

T1 - DeepAPI#

T2 - 2nd Conference on Software Engineering and Information Management, SEIM 2017

AU - Chebykin, Alexander

AU - Kita, Mikhail

AU - Kirilenko, Iakov

PY - 2017/1/1

Y1 - 2017/1/1

N2 - Developers often search for an implementation of typical features via libraries (for example, how to create a UI button control, extract data from a JSON-formatted file, etc.). The Internet is the usual source of the information on the topic. However, various statistical tools provide an alternative: after processing large amounts of source code and learning common patterns, they can convert a user request to a set of relevant function calls. We examine one of those tools - DeepAPI. This fresh deep learning based algorithm outperforms all others (according to its authors). We attempt to reproduce this result using different target programming language - C# - instead of Java used in the original DeepAPI. In this paper we report arising problems in the data gathering for training, difficulties in the model construction and training, and finally discuss possible modifications of the algorithm.

AB - Developers often search for an implementation of typical features via libraries (for example, how to create a UI button control, extract data from a JSON-formatted file, etc.). The Internet is the usual source of the information on the topic. However, various statistical tools provide an alternative: after processing large amounts of source code and learning common patterns, they can convert a user request to a set of relevant function calls. We examine one of those tools - DeepAPI. This fresh deep learning based algorithm outperforms all others (according to its authors). We attempt to reproduce this result using different target programming language - C# - instead of Java used in the original DeepAPI. In this paper we report arising problems in the data gathering for training, difficulties in the model construction and training, and finally discuss possible modifications of the algorithm.

UR - http://www.scopus.com/inward/record.url?scp=85025164732&partnerID=8YFLogxK

M3 - Conference article

AN - SCOPUS:85025164732

VL - 1864

JO - CEUR Workshop Proceedings

JF - CEUR Workshop Proceedings

SN - 1613-0073

Y2 - 21 April 2017

ER -

ID: 36436898