Work

Time-Efficient Code Completion Model for the R Programming Language

Year: 2021

Type: conference-paper

Abstract: In this paper, we present a deep learning code completion model for the R programming language.We introduce several techniques to utilize language modeling based architecture in the code completion task.With these techniques, the model requires low resources, but still achieves high quality.We also present an evaluation dataset for the R programming language completion task.Our dataset contains multiple autocompletion usage contexts and that provides robust validation results.The dataset is publicly available.1 https://github.com/arti32lehtonen/ rcompletion evaluation dataset

DOI: 10.18653/v1/2021.nlp4prog-1.4

Authors: Artem Popov, Dmitrii Orekhov, Denis Litvinov, Nikolay Korolev, Gleb Morgachev

Institutions: Moscow Institute of Physics and Technology, ITMO University, Lomonosov Moscow State University

Language: English

Topic: Software Engineering Research

Subfield: Information Systems

Field: Computer Science

Domain: Physical Sciences

Open Access status: gold

OpenAlex ID: W3186370931

FWCI: 0.502

Cites: 19

Cited by: 7

Related to: 10