DeepAPI#: CLR/C# call sequence synthesis from text query

Alexander Chebykin, Mikhail Kita, Iakov Kirilenko

Результат исследований: Научные публикации в периодических изданияхстатья в журнале по материалам конференциирецензирование


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.

Язык оригиналаанглийский
ЖурналCEUR Workshop Proceedings
СостояниеОпубликовано - 1 янв 2017
Событие2nd Conference on Software Engineering and Information Management, SEIM 2017 - Saint Petersburg, Российская Федерация
Продолжительность: 21 апр 2017 → …

Предметные области Scopus

  • Компьютерные науки (все)


Подробные сведения о темах исследования «DeepAPI#: CLR/C# call sequence synthesis from text query». Вместе они формируют уникальный семантический отпечаток (fingerprint).