Print Email Facebook Twitter Enriching Source Code with Contextual Data for Code Completion Models Title Enriching Source Code with Contextual Data for Code Completion Models: An Empirical Study Author van Dam, Tim (Student TU Delft) Izadi, M. (TU Delft Software Engineering) van Deursen, A. (TU Delft Software Technology) Contributor O'Conner, L. (editor) Department Software Technology Date 2023 Abstract Transformer-based pre-trained models have recently achieved great results in solving many software engineering tasks including automatic code completion which is a staple in a developer’s toolkit. While many have striven to improve the code-understanding abilities of such models, the opposite – making the code easier to understand – has not been properly investigated. In this study, we aim to answer whether making code easier to understand through using contextual data improves the performance of pre-trained code language models for the task of code completion. We consider type annotations and comments as two common forms of additional contextual information that often help developers understand code better. For the experiments, we study code completion in two granularity levels; token and line completion and take three recent and large-scale language models for source code: UniXcoder, CodeGPT, and InCoder with five evaluation metrics. Finally, we perform the Wilcoxon Signed Rank test to gauge significance and measure the effect size. Contrary to our expectations, all models perform better if type annotations are removed (albeit the effect sizes are small). For comments, we find that the models perform better in the presence of multi-line comments (again with small effect sizes). Based on our observations, we recommend making proper design choices when training, fine-tuning, or simply selecting such models given the intended data and application. Better evaluations and multimodal techniques can also be further investigated to improve the practicality and accuracy of auto-completions. Subject Code CompletionPre-trained Language ModelsContextEmpirical Software Engineering To reference this document use: http://resolver.tudelft.nl/uuid:69c13738-0f23-42d5-845d-3312381e3b94 DOI https://doi.org/10.1109/MSR59073.2023.00035 Publisher IEEE, Piscataway Embargo date 2024-01-12 ISBN 979-8-3503-1185-3 Source Proceedings of the 2023 IEEE/ACM 20th International Conference on Mining Software Repositories (MSR) Event 2023 IEEE/ACM 20th International Conference on Mining Software Repositories (MSR), 2023-05-15 → 2023-05-16, Melbourne, Australia Series Proceedings - 2023 IEEE/ACM 20th International Conference on Mining Software Repositories, MSR 2023 Bibliographical note Green Open Access added to TU Delft Institutional Repository 'You share, we take care!' - Taverne project https://www.openaccess.nl/en/you-share-we-take-care Otherwise as indicated in the copyright section: the publisher is the copyright holder of this work and the author uses the Dutch legislation to make this work public. Part of collection Institutional Repository Document type conference paper Rights © 2023 Tim van Dam, M. Izadi, A. van Deursen Files PDF Enriching_Source_Code_wit ... _Study.pdf 1.03 MB Close viewer /islandora/object/uuid:69c13738-0f23-42d5-845d-3312381e3b94/datastream/OBJ/view