Cross-lingual Performance of CodeGPT on the Code Completion Task

Bachelor Thesis (2023)
Authors

H.N. Kuo (TU Delft - Electrical Engineering, Mathematics and Computer Science)

Supervisors

Maliheh Izadi (TU Delft - Software Engineering)

Jonathan Katzy (TU Delft - Software Engineering)

Arie Van Deursen (TU Delft - Software Technology)

Faculty
Electrical Engineering, Mathematics and Computer Science, Electrical Engineering, Mathematics and Computer Science
Copyright
© 2023 Nadine Kuo
More Info
expand_more
Publication Year
2023
Language
English
Copyright
© 2023 Nadine Kuo
Graduation Date
28-06-2023
Awarding Institution
Delft University of Technology
Project
CSE3000 Research Project
Programme
Computer Science and Engineering
Faculty
Electrical Engineering, Mathematics and Computer Science, Electrical Engineering, Mathematics and Computer Science
Reuse Rights

Other than for strictly personal use, it is not permitted to download, forward or distribute the text or part of it, without the consent of the author(s) and/or copyright holder(s), unless the work is under an open content license such as Creative Commons.

Abstract

The development of contemporary source code auto-completion tools have significantly boosted productivity and efficiency of developers. In 2021, the GPT-2-based Transformer CodeGPT was developed to support code completion and text-to-code generation. Similarly to most code models however, CodeGPT was trained on a limited set of widely-used languages (Java, Python) - leading to constrained efficacy in lower-resource languages. This motivated us to research CodeGPT's performance on the token-level code completion task across high- and low-resource languages. We investigate in which scenarios CodeGPT predicts incorrect tokens with high certainty using a tuned lens, followed by studying attention patterns that underlie the observed behaviour. Our findings indicate that CodeGPT is most competent in Java and Python code (Top-1 accuracies: 69.2% and 68.2% respectively). It generates false predictions with highest confidence when it encounters unfamiliar constructs in low-resource languages, or code structures that cannot be predicted from left context only. Moreover, we find a positive correlation between null attention and model confidence.

Files

CodeShop_Nadine.pdf
(pdf | 1.38 Mb)
License info not available